Add files using upload-large-folder tool
Browse files- chat_template.jinja +47 -0
- config.json +58 -58
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +2 -2
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +368 -383
- tokenizer_config.json +0 -1
chat_template.jinja
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}
|
| 2 |
+
{%- if messages[0]['role'] == 'system' -%}
|
| 3 |
+
{%- if messages[0]['content'] is string -%}
|
| 4 |
+
{%- set first_user_prefix = messages[0]['content'] + '
|
| 5 |
+
|
| 6 |
+
' -%}
|
| 7 |
+
{%- else -%}
|
| 8 |
+
{%- set first_user_prefix = messages[0]['content'][0]['text'] + '
|
| 9 |
+
|
| 10 |
+
' -%}
|
| 11 |
+
{%- endif -%}
|
| 12 |
+
{%- set loop_messages = messages[1:] -%}
|
| 13 |
+
{%- else -%}
|
| 14 |
+
{%- set first_user_prefix = "" -%}
|
| 15 |
+
{%- set loop_messages = messages -%}
|
| 16 |
+
{%- endif -%}
|
| 17 |
+
{%- for message in loop_messages -%}
|
| 18 |
+
{%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
|
| 19 |
+
{{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if (message['role'] == 'assistant') -%}
|
| 22 |
+
{%- set role = "model" -%}
|
| 23 |
+
{%- else -%}
|
| 24 |
+
{%- set role = message['role'] -%}
|
| 25 |
+
{%- endif -%}
|
| 26 |
+
{{ '<start_of_turn>' + role + '
|
| 27 |
+
' + (first_user_prefix if loop.first else "") }}
|
| 28 |
+
{%- if message['content'] is string -%}
|
| 29 |
+
{{ message['content'] | trim }}
|
| 30 |
+
{%- elif message['content'] is iterable -%}
|
| 31 |
+
{%- for item in message['content'] -%}
|
| 32 |
+
{%- if item['type'] == 'image' -%}
|
| 33 |
+
{{ '<start_of_image>' }}
|
| 34 |
+
{%- elif item['type'] == 'text' -%}
|
| 35 |
+
{{ item['text'] | trim }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endfor -%}
|
| 38 |
+
{%- else -%}
|
| 39 |
+
{{ raise_exception("Invalid content type") }}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{ '<end_of_turn>
|
| 42 |
+
' }}
|
| 43 |
+
{%- endfor -%}
|
| 44 |
+
{%- if add_generation_prompt -%}
|
| 45 |
+
{{'<start_of_turn>model
|
| 46 |
+
'}}
|
| 47 |
+
{%- endif -%}
|
config.json
CHANGED
|
@@ -25,81 +25,81 @@
|
|
| 25 |
"multi_modal_projector",
|
| 26 |
"merger",
|
| 27 |
"modality_projection",
|
| 28 |
-
"language_model.model.layers.
|
| 29 |
-
"language_model.model.layers.
|
| 30 |
-
"language_model.model.layers.
|
| 31 |
-
"language_model.model.layers.
|
| 32 |
"language_model.model.layers.6.self_attn",
|
| 33 |
-
"language_model.model.layers.
|
| 34 |
-
"
|
| 35 |
-
"language_model.model.layers.
|
| 36 |
-
"language_model.model.layers.
|
|
|
|
| 37 |
"language_model.model.layers.5.self_attn",
|
| 38 |
-
"language_model.model.layers.2.mlp",
|
| 39 |
-
"language_model.model.layers.4.mlp",
|
| 40 |
-
"language_model.model.layers.5.mlp",
|
| 41 |
"language_model.model.layers.9.mlp",
|
| 42 |
-
"language_model.model.layers.7.self_attn",
|
| 43 |
-
"language_model.model.layers.6.mlp",
|
| 44 |
-
"language_model.model.layers.8.mlp",
|
| 45 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn",
|
| 46 |
-
"language_model.model.layers.7.mlp",
|
| 47 |
-
"language_model.model.layers.3.self_attn",
|
| 48 |
-
"language_model.model.layers.11.mlp",
|
| 49 |
"language_model.model.layers.3.mlp",
|
|
|
|
|
|
|
| 50 |
"vision_tower.vision_model.encoder.layers.19.self_attn",
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn",
|
| 54 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn",
|
| 55 |
-
"vision_tower.vision_model.encoder.layers.17.mlp",
|
| 56 |
-
"vision_tower.vision_model.encoder.layers.24.self_attn",
|
| 57 |
-
"vision_tower.vision_model.encoder.layers.24.mlp",
|
| 58 |
-
"vision_tower.vision_model.encoder.layers.26.self_attn",
|
| 59 |
-
"vision_tower.vision_model.encoder.layers.20.mlp",
|
| 60 |
"vision_tower.vision_model.encoder.layers.20.self_attn",
|
| 61 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"vision_tower.vision_model.encoder.layers.19.mlp",
|
| 63 |
-
"vision_tower.vision_model.encoder.layers.
|
| 64 |
-
"vision_tower.vision_model.encoder.layers.
|
| 65 |
-
"vision_tower.vision_model.encoder.layers.
|
| 66 |
-
"
|
| 67 |
-
"vision_tower.vision_model.encoder.layers.16.mlp",
|
| 68 |
"vision_tower.vision_model.encoder.layers.25.mlp",
|
| 69 |
-
"vision_tower.vision_model.encoder.layers.15.mlp",
|
| 70 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn",
|
| 71 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn",
|
| 72 |
-
"vision_tower.vision_model.encoder.layers.10.mlp",
|
| 73 |
"vision_tower.vision_model.encoder.layers.17.self_attn",
|
| 74 |
-
"vision_tower.vision_model.encoder.layers.
|
| 75 |
-
"vision_tower.vision_model.encoder.layers.
|
| 76 |
-
"vision_tower.vision_model.encoder.layers.
|
| 77 |
-
"vision_tower.vision_model.encoder.layers.
|
| 78 |
"vision_tower.vision_model.encoder.layers.22.mlp",
|
| 79 |
-
"vision_tower.vision_model.encoder.layers.
|
| 80 |
-
"vision_tower.vision_model.encoder.layers.
|
| 81 |
-
"vision_tower.vision_model.encoder.layers.
|
|
|
|
|
|
|
| 82 |
"vision_tower.vision_model.encoder.layers.7.mlp",
|
| 83 |
-
"vision_tower.vision_model.encoder.layers.6.mlp",
|
| 84 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn",
|
| 85 |
"vision_tower.vision_model.encoder.layers.9.self_attn",
|
| 86 |
-
"vision_tower.vision_model.encoder.layers.
|
|
|
|
|
|
|
| 87 |
"vision_tower.vision_model.encoder.layers.5.mlp",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
"vision_tower.vision_model.encoder.layers.8.mlp",
|
| 89 |
-
"vision_tower.vision_model.encoder.layers.
|
| 90 |
"vision_tower.vision_model.encoder.layers.6.self_attn",
|
| 91 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn",
|
| 92 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn",
|
| 93 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn",
|
| 94 |
-
"vision_tower.vision_model.encoder.layers.0.self_attn",
|
| 95 |
-
"vision_tower.vision_model.encoder.layers.3.mlp",
|
| 96 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn",
|
| 97 |
-
"vision_tower.vision_model.encoder.layers.2.mlp",
|
| 98 |
"vision_tower.vision_model.encoder.layers.5.self_attn",
|
|
|
|
| 99 |
"vision_tower.vision_model.encoder.layers.3.self_attn",
|
| 100 |
-
"vision_tower.vision_model.encoder.layers.
|
|
|
|
|
|
|
| 101 |
"vision_tower.vision_model.encoder.layers.26.mlp",
|
| 102 |
-
"vision_tower.vision_model.encoder.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
],
|
| 104 |
"llm_int8_threshold": 6.0,
|
| 105 |
"load_in_4bit": true,
|
|
@@ -137,7 +137,7 @@
|
|
| 137 |
"vocab_size": 262208
|
| 138 |
},
|
| 139 |
"torch_dtype": "bfloat16",
|
| 140 |
-
"transformers_version": "4.
|
| 141 |
"unsloth_fixed": true,
|
| 142 |
"vision_config": {
|
| 143 |
"attention_dropout": 0.0,
|
|
|
|
| 25 |
"multi_modal_projector",
|
| 26 |
"merger",
|
| 27 |
"modality_projection",
|
| 28 |
+
"language_model.model.layers.22.self_attn",
|
| 29 |
+
"language_model.model.layers.18.self_attn",
|
| 30 |
+
"language_model.model.layers.8.mlp",
|
| 31 |
+
"language_model.model.layers.11.mlp",
|
| 32 |
"language_model.model.layers.6.self_attn",
|
| 33 |
+
"language_model.model.layers.19.self_attn",
|
| 34 |
+
"vision_tower.vision_model.encoder.layers.24.self_attn",
|
| 35 |
+
"language_model.model.layers.14.self_attn",
|
| 36 |
+
"language_model.model.layers.7.self_attn",
|
| 37 |
+
"language_model.model.layers.17.mlp",
|
| 38 |
"language_model.model.layers.5.self_attn",
|
|
|
|
|
|
|
|
|
|
| 39 |
"language_model.model.layers.9.mlp",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
"language_model.model.layers.3.mlp",
|
| 41 |
+
"language_model.model.layers.3.self_attn",
|
| 42 |
+
"language_model.model.layers.7.mlp",
|
| 43 |
"vision_tower.vision_model.encoder.layers.19.self_attn",
|
| 44 |
+
"language_model.model.layers.15.mlp",
|
| 45 |
+
"language_model.model.layers.11.self_attn",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"vision_tower.vision_model.encoder.layers.20.self_attn",
|
| 47 |
+
"language_model.model.layers.4.mlp",
|
| 48 |
+
"vision_tower.vision_model.encoder.layers.26.self_attn",
|
| 49 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn",
|
| 50 |
+
"language_model.model.layers.5.mlp",
|
| 51 |
+
"language_model.model.layers.13.mlp",
|
| 52 |
+
"language_model.model.layers.2.mlp",
|
| 53 |
"vision_tower.vision_model.encoder.layers.19.mlp",
|
| 54 |
+
"vision_tower.vision_model.encoder.layers.25.self_attn",
|
| 55 |
+
"vision_tower.vision_model.encoder.layers.24.mlp",
|
| 56 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn",
|
| 57 |
+
"language_model.model.layers.6.mlp",
|
|
|
|
| 58 |
"vision_tower.vision_model.encoder.layers.25.mlp",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
"vision_tower.vision_model.encoder.layers.17.self_attn",
|
| 60 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn",
|
| 61 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn",
|
| 62 |
+
"vision_tower.vision_model.encoder.layers.21.mlp",
|
| 63 |
+
"vision_tower.vision_model.encoder.layers.13.mlp",
|
| 64 |
"vision_tower.vision_model.encoder.layers.22.mlp",
|
| 65 |
+
"vision_tower.vision_model.encoder.layers.17.mlp",
|
| 66 |
+
"vision_tower.vision_model.encoder.layers.20.mlp",
|
| 67 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn",
|
| 68 |
+
"vision_tower.vision_model.encoder.layers.16.mlp",
|
| 69 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn",
|
| 70 |
"vision_tower.vision_model.encoder.layers.7.mlp",
|
|
|
|
|
|
|
| 71 |
"vision_tower.vision_model.encoder.layers.9.self_attn",
|
| 72 |
+
"vision_tower.vision_model.encoder.layers.15.mlp",
|
| 73 |
+
"vision_tower.vision_model.encoder.layers.18.mlp",
|
| 74 |
+
"vision_tower.vision_model.encoder.layers.12.mlp",
|
| 75 |
"vision_tower.vision_model.encoder.layers.5.mlp",
|
| 76 |
+
"vision_tower.vision_model.encoder.layers.9.mlp",
|
| 77 |
+
"vision_tower.vision_model.encoder.layers.14.mlp",
|
| 78 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn",
|
| 79 |
+
"vision_tower.vision_model.encoder.layers.11.mlp",
|
| 80 |
+
"vision_tower.vision_model.encoder.layers.10.mlp",
|
| 81 |
+
"vision_tower.vision_model.encoder.layers.23.mlp",
|
| 82 |
"vision_tower.vision_model.encoder.layers.8.mlp",
|
| 83 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn",
|
| 84 |
"vision_tower.vision_model.encoder.layers.6.self_attn",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
"vision_tower.vision_model.encoder.layers.5.self_attn",
|
| 86 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn",
|
| 87 |
"vision_tower.vision_model.encoder.layers.3.self_attn",
|
| 88 |
+
"vision_tower.vision_model.encoder.layers.4.mlp",
|
| 89 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn",
|
| 90 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn",
|
| 91 |
"vision_tower.vision_model.encoder.layers.26.mlp",
|
| 92 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn",
|
| 93 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn",
|
| 94 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn",
|
| 95 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn",
|
| 96 |
+
"vision_tower.vision_model.encoder.layers.3.mlp",
|
| 97 |
+
"vision_tower.vision_model.encoder.layers.6.mlp",
|
| 98 |
+
"vision_tower.vision_model.encoder.layers.2.mlp",
|
| 99 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn",
|
| 100 |
+
"vision_tower.vision_model.encoder.layers.1.mlp",
|
| 101 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn",
|
| 102 |
+
"vision_tower.vision_model.encoder.layers.0.mlp"
|
| 103 |
],
|
| 104 |
"llm_int8_threshold": 6.0,
|
| 105 |
"load_in_4bit": true,
|
|
|
|
| 137 |
"vocab_size": 262208
|
| 138 |
},
|
| 139 |
"torch_dtype": "bfloat16",
|
| 140 |
+
"transformers_version": "4.52.0.dev0",
|
| 141 |
"unsloth_fixed": true,
|
| 142 |
"vision_config": {
|
| 143 |
"attention_dropout": 0.0,
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"pad_token_id": 0,
|
| 10 |
"top_k": 64,
|
| 11 |
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "4.
|
| 13 |
}
|
|
|
|
| 9 |
"pad_token_id": 0,
|
| 10 |
"top_k": 64,
|
| 11 |
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.52.0.dev0"
|
| 13 |
}
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e329a638c49d6f8e6d8649198401c24ca2e075ab32ac3ff0613de933b64abdf6
|
| 3 |
+
size 4953233186
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c73460988ff2f0faf63d0be2e39271cce9b84658eb49cd6a4e1b7e66d5363e32
|
| 3 |
+
size 4978202196
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7850b744104a7591a92439ed18e2e20499d23cef4616c5ba24bc68c38a99ff71
|
| 3 |
+
size 2258633570
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
|
@@ -54,8 +54,23 @@
|
|
| 54 |
"language_model.model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 55 |
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 56 |
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 60 |
"language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 61 |
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
|
@@ -87,8 +102,23 @@
|
|
| 87 |
"language_model.model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 88 |
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 89 |
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 93 |
"language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
@@ -127,34 +157,29 @@
|
|
| 127 |
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 128 |
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 129 |
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 130 |
-
"language_model.model.layers.11.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 131 |
-
"language_model.model.layers.11.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 132 |
-
"language_model.model.layers.11.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 133 |
-
"language_model.model.layers.11.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 134 |
-
"language_model.model.layers.11.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 135 |
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
-
"language_model.model.layers.11.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 137 |
-
"language_model.model.layers.11.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 138 |
-
"language_model.model.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 139 |
-
"language_model.model.layers.11.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 140 |
-
"language_model.model.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 141 |
"language_model.model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 142 |
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
-
"language_model.model.layers.11.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 144 |
-
"language_model.model.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 145 |
-
"language_model.model.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 146 |
-
"language_model.model.layers.11.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 147 |
-
"language_model.model.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 148 |
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
-
"language_model.model.layers.11.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 150 |
-
"language_model.model.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 151 |
-
"language_model.model.layers.11.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 152 |
-
"language_model.model.layers.11.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 153 |
-
"language_model.model.layers.11.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 154 |
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 155 |
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 157 |
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 159 |
"language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 160 |
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
@@ -219,56 +244,36 @@
|
|
| 219 |
"language_model.model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 220 |
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 221 |
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 222 |
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 223 |
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 224 |
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 225 |
"language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 226 |
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 227 |
"language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 228 |
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
-
"language_model.model.layers.14.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 230 |
-
"language_model.model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 231 |
-
"language_model.model.layers.14.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 232 |
-
"language_model.model.layers.14.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 233 |
-
"language_model.model.layers.14.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 234 |
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
-
"language_model.model.layers.14.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 236 |
-
"language_model.model.layers.14.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 237 |
-
"language_model.model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 238 |
-
"language_model.model.layers.14.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 239 |
-
"language_model.model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 240 |
"language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 241 |
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 242 |
-
"language_model.model.layers.14.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 243 |
-
"language_model.model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 244 |
-
"language_model.model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 245 |
-
"language_model.model.layers.14.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 246 |
-
"language_model.model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 247 |
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 248 |
-
"language_model.model.layers.14.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 249 |
-
"language_model.model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 250 |
-
"language_model.model.layers.14.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 251 |
-
"language_model.model.layers.14.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 252 |
-
"language_model.model.layers.14.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 253 |
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 254 |
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 255 |
-
"language_model.model.layers.15.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 256 |
-
"language_model.model.layers.15.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 257 |
-
"language_model.model.layers.15.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 258 |
-
"language_model.model.layers.15.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 259 |
-
"language_model.model.layers.15.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 260 |
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 261 |
-
"language_model.model.layers.15.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 262 |
-
"language_model.model.layers.15.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 263 |
-
"language_model.model.layers.15.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 264 |
-
"language_model.model.layers.15.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 265 |
-
"language_model.model.layers.15.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 266 |
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 267 |
-
"language_model.model.layers.15.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 268 |
-
"language_model.model.layers.15.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 269 |
-
"language_model.model.layers.15.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 270 |
-
"language_model.model.layers.15.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 271 |
-
"language_model.model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 272 |
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 273 |
"language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 274 |
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
@@ -300,8 +305,23 @@
|
|
| 300 |
"language_model.model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 301 |
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 302 |
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 303 |
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 304 |
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 305 |
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 306 |
"language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 307 |
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
@@ -333,23 +353,8 @@
|
|
| 333 |
"language_model.model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 334 |
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 335 |
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 336 |
-
"language_model.model.layers.17.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 337 |
-
"language_model.model.layers.17.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 338 |
-
"language_model.model.layers.17.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 339 |
-
"language_model.model.layers.17.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 340 |
-
"language_model.model.layers.17.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 341 |
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
-
"language_model.model.layers.17.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 343 |
-
"language_model.model.layers.17.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 344 |
-
"language_model.model.layers.17.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 345 |
-
"language_model.model.layers.17.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 346 |
-
"language_model.model.layers.17.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 347 |
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 348 |
-
"language_model.model.layers.17.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 349 |
-
"language_model.model.layers.17.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 350 |
-
"language_model.model.layers.17.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 351 |
-
"language_model.model.layers.17.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 352 |
-
"language_model.model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 353 |
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 354 |
"language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 355 |
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
@@ -403,30 +408,10 @@
|
|
| 403 |
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 404 |
"language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 405 |
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 406 |
-
"language_model.model.layers.18.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 407 |
-
"language_model.model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 408 |
-
"language_model.model.layers.18.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 409 |
-
"language_model.model.layers.18.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 410 |
-
"language_model.model.layers.18.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 411 |
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 412 |
-
"language_model.model.layers.18.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 413 |
-
"language_model.model.layers.18.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 414 |
-
"language_model.model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 415 |
-
"language_model.model.layers.18.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 416 |
-
"language_model.model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 417 |
"language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 418 |
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 419 |
-
"language_model.model.layers.18.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 420 |
-
"language_model.model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 421 |
-
"language_model.model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 422 |
-
"language_model.model.layers.18.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 423 |
-
"language_model.model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 424 |
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 425 |
-
"language_model.model.layers.18.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 426 |
-
"language_model.model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 427 |
-
"language_model.model.layers.18.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 428 |
-
"language_model.model.layers.18.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 429 |
-
"language_model.model.layers.18.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 430 |
"language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 431 |
"language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 432 |
"language_model.model.layers.19.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
|
@@ -451,30 +436,10 @@
|
|
| 451 |
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 452 |
"language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 453 |
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 454 |
-
"language_model.model.layers.19.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 455 |
-
"language_model.model.layers.19.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 456 |
-
"language_model.model.layers.19.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 457 |
-
"language_model.model.layers.19.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 458 |
-
"language_model.model.layers.19.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 459 |
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 460 |
-
"language_model.model.layers.19.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 461 |
-
"language_model.model.layers.19.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 462 |
-
"language_model.model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 463 |
-
"language_model.model.layers.19.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 464 |
-
"language_model.model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 465 |
"language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 466 |
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 467 |
-
"language_model.model.layers.19.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 468 |
-
"language_model.model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 469 |
-
"language_model.model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 470 |
-
"language_model.model.layers.19.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 471 |
-
"language_model.model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 472 |
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 473 |
-
"language_model.model.layers.19.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 474 |
-
"language_model.model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 475 |
-
"language_model.model.layers.19.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 476 |
-
"language_model.model.layers.19.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 477 |
-
"language_model.model.layers.19.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 478 |
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 479 |
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 480 |
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
|
@@ -484,10 +449,30 @@
|
|
| 484 |
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 485 |
"language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 486 |
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 487 |
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 488 |
"language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 489 |
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 490 |
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 491 |
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 492 |
"language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 493 |
"language_model.model.layers.20.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
|
@@ -608,52 +593,32 @@
|
|
| 608 |
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 609 |
"language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 610 |
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 611 |
-
"language_model.model.layers.22.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 612 |
-
"language_model.model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 613 |
-
"language_model.model.layers.22.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 614 |
-
"language_model.model.layers.22.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 615 |
-
"language_model.model.layers.22.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 616 |
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 617 |
-
"language_model.model.layers.22.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 618 |
-
"language_model.model.layers.22.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 619 |
-
"language_model.model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 620 |
-
"language_model.model.layers.22.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 621 |
-
"language_model.model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 622 |
"language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 623 |
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
-
"language_model.model.layers.22.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 625 |
-
"language_model.model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 626 |
-
"language_model.model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 627 |
-
"language_model.model.layers.22.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 628 |
-
"language_model.model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 629 |
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 630 |
-
"language_model.model.layers.
|
| 631 |
-
"language_model.model.layers.
|
| 632 |
-
"language_model.model.layers.
|
| 633 |
-
"language_model.model.layers.
|
| 634 |
-
"language_model.model.layers.
|
| 635 |
-
"language_model.model.layers.23.
|
| 636 |
-
"language_model.model.layers.23.mlp.down_proj.weight": "model-
|
| 637 |
-
"language_model.model.layers.23.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
|
| 638 |
-
"language_model.model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
|
| 639 |
-
"language_model.model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
|
| 640 |
-
"language_model.model.layers.23.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
|
| 641 |
-
"language_model.model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
|
| 642 |
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 643 |
"language_model.model.layers.23.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 644 |
"language_model.model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 645 |
"language_model.model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 646 |
"language_model.model.layers.23.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 647 |
"language_model.model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 648 |
-
"language_model.model.layers.23.mlp.up_proj.weight": "model-
|
| 649 |
-
"language_model.model.layers.23.mlp.up_proj.weight.absmax": "model-
|
| 650 |
-
"language_model.model.layers.23.mlp.up_proj.weight.nested_absmax": "model-
|
| 651 |
-
"language_model.model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-
|
| 652 |
-
"language_model.model.layers.23.mlp.up_proj.weight.quant_map": "model-
|
| 653 |
-
"language_model.model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 654 |
-
"language_model.model.layers.23.post_attention_layernorm.weight": "model-
|
| 655 |
-
"language_model.model.layers.23.post_feedforward_layernorm.weight": "model-
|
| 656 |
-
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-
|
| 657 |
"language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 658 |
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 659 |
"language_model.model.layers.23.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
|
@@ -680,198 +645,198 @@
|
|
| 680 |
"language_model.model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 681 |
"language_model.model.layers.23.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 682 |
"language_model.model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 683 |
-
"language_model.model.layers.24.input_layernorm.weight": "model-
|
| 684 |
-
"language_model.model.layers.24.mlp.down_proj.weight": "model-
|
| 685 |
-
"language_model.model.layers.24.mlp.down_proj.weight.absmax": "model-
|
| 686 |
-
"language_model.model.layers.24.mlp.down_proj.weight.nested_absmax": "model-
|
| 687 |
-
"language_model.model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-
|
| 688 |
-
"language_model.model.layers.24.mlp.down_proj.weight.quant_map": "model-
|
| 689 |
-
"language_model.model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 690 |
-
"language_model.model.layers.24.mlp.gate_proj.weight": "model-
|
| 691 |
-
"language_model.model.layers.24.mlp.gate_proj.weight.absmax": "model-
|
| 692 |
-
"language_model.model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-
|
| 693 |
-
"language_model.model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 694 |
-
"language_model.model.layers.24.mlp.gate_proj.weight.quant_map": "model-
|
| 695 |
-
"language_model.model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 696 |
-
"language_model.model.layers.24.mlp.up_proj.weight": "model-
|
| 697 |
-
"language_model.model.layers.24.mlp.up_proj.weight.absmax": "model-
|
| 698 |
-
"language_model.model.layers.24.mlp.up_proj.weight.nested_absmax": "model-
|
| 699 |
-
"language_model.model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-
|
| 700 |
-
"language_model.model.layers.24.mlp.up_proj.weight.quant_map": "model-
|
| 701 |
-
"language_model.model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 702 |
-
"language_model.model.layers.24.post_attention_layernorm.weight": "model-
|
| 703 |
-
"language_model.model.layers.24.post_feedforward_layernorm.weight": "model-
|
| 704 |
-
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-
|
| 705 |
-
"language_model.model.layers.24.self_attn.k_norm.weight": "model-
|
| 706 |
-
"language_model.model.layers.24.self_attn.k_proj.weight": "model-
|
| 707 |
-
"language_model.model.layers.24.self_attn.k_proj.weight.absmax": "model-
|
| 708 |
-
"language_model.model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-
|
| 709 |
-
"language_model.model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 710 |
-
"language_model.model.layers.24.self_attn.k_proj.weight.quant_map": "model-
|
| 711 |
-
"language_model.model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 712 |
-
"language_model.model.layers.24.self_attn.o_proj.weight": "model-
|
| 713 |
-
"language_model.model.layers.24.self_attn.o_proj.weight.absmax": "model-
|
| 714 |
-
"language_model.model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-
|
| 715 |
-
"language_model.model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 716 |
-
"language_model.model.layers.24.self_attn.o_proj.weight.quant_map": "model-
|
| 717 |
-
"language_model.model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 718 |
-
"language_model.model.layers.24.self_attn.q_norm.weight": "model-
|
| 719 |
-
"language_model.model.layers.24.self_attn.q_proj.weight": "model-
|
| 720 |
-
"language_model.model.layers.24.self_attn.q_proj.weight.absmax": "model-
|
| 721 |
-
"language_model.model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-
|
| 722 |
-
"language_model.model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 723 |
-
"language_model.model.layers.24.self_attn.q_proj.weight.quant_map": "model-
|
| 724 |
-
"language_model.model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 725 |
-
"language_model.model.layers.24.self_attn.v_proj.weight": "model-
|
| 726 |
-
"language_model.model.layers.24.self_attn.v_proj.weight.absmax": "model-
|
| 727 |
-
"language_model.model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-
|
| 728 |
-
"language_model.model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 729 |
-
"language_model.model.layers.24.self_attn.v_proj.weight.quant_map": "model-
|
| 730 |
-
"language_model.model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 731 |
-
"language_model.model.layers.25.input_layernorm.weight": "model-
|
| 732 |
-
"language_model.model.layers.25.mlp.down_proj.weight": "model-
|
| 733 |
-
"language_model.model.layers.25.mlp.down_proj.weight.absmax": "model-
|
| 734 |
-
"language_model.model.layers.25.mlp.down_proj.weight.nested_absmax": "model-
|
| 735 |
-
"language_model.model.layers.25.mlp.down_proj.weight.nested_quant_map": "model-
|
| 736 |
-
"language_model.model.layers.25.mlp.down_proj.weight.quant_map": "model-
|
| 737 |
-
"language_model.model.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 738 |
-
"language_model.model.layers.25.mlp.gate_proj.weight": "model-
|
| 739 |
-
"language_model.model.layers.25.mlp.gate_proj.weight.absmax": "model-
|
| 740 |
-
"language_model.model.layers.25.mlp.gate_proj.weight.nested_absmax": "model-
|
| 741 |
-
"language_model.model.layers.25.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 742 |
-
"language_model.model.layers.25.mlp.gate_proj.weight.quant_map": "model-
|
| 743 |
-
"language_model.model.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 744 |
-
"language_model.model.layers.25.mlp.up_proj.weight": "model-
|
| 745 |
-
"language_model.model.layers.25.mlp.up_proj.weight.absmax": "model-
|
| 746 |
-
"language_model.model.layers.25.mlp.up_proj.weight.nested_absmax": "model-
|
| 747 |
-
"language_model.model.layers.25.mlp.up_proj.weight.nested_quant_map": "model-
|
| 748 |
-
"language_model.model.layers.25.mlp.up_proj.weight.quant_map": "model-
|
| 749 |
-
"language_model.model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 750 |
-
"language_model.model.layers.25.post_attention_layernorm.weight": "model-
|
| 751 |
-
"language_model.model.layers.25.post_feedforward_layernorm.weight": "model-
|
| 752 |
-
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-
|
| 753 |
-
"language_model.model.layers.25.self_attn.k_norm.weight": "model-
|
| 754 |
-
"language_model.model.layers.25.self_attn.k_proj.weight": "model-
|
| 755 |
-
"language_model.model.layers.25.self_attn.k_proj.weight.absmax": "model-
|
| 756 |
-
"language_model.model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-
|
| 757 |
-
"language_model.model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 758 |
-
"language_model.model.layers.25.self_attn.k_proj.weight.quant_map": "model-
|
| 759 |
-
"language_model.model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 760 |
-
"language_model.model.layers.25.self_attn.o_proj.weight": "model-
|
| 761 |
-
"language_model.model.layers.25.self_attn.o_proj.weight.absmax": "model-
|
| 762 |
-
"language_model.model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-
|
| 763 |
-
"language_model.model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 764 |
-
"language_model.model.layers.25.self_attn.o_proj.weight.quant_map": "model-
|
| 765 |
-
"language_model.model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 766 |
-
"language_model.model.layers.25.self_attn.q_norm.weight": "model-
|
| 767 |
-
"language_model.model.layers.25.self_attn.q_proj.weight": "model-
|
| 768 |
-
"language_model.model.layers.25.self_attn.q_proj.weight.absmax": "model-
|
| 769 |
-
"language_model.model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-
|
| 770 |
-
"language_model.model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 771 |
-
"language_model.model.layers.25.self_attn.q_proj.weight.quant_map": "model-
|
| 772 |
-
"language_model.model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 773 |
-
"language_model.model.layers.25.self_attn.v_proj.weight": "model-
|
| 774 |
-
"language_model.model.layers.25.self_attn.v_proj.weight.absmax": "model-
|
| 775 |
-
"language_model.model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-
|
| 776 |
-
"language_model.model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 777 |
-
"language_model.model.layers.25.self_attn.v_proj.weight.quant_map": "model-
|
| 778 |
-
"language_model.model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 779 |
-
"language_model.model.layers.26.input_layernorm.weight": "model-
|
| 780 |
-
"language_model.model.layers.26.mlp.down_proj.weight": "model-
|
| 781 |
-
"language_model.model.layers.26.mlp.down_proj.weight.absmax": "model-
|
| 782 |
-
"language_model.model.layers.26.mlp.down_proj.weight.nested_absmax": "model-
|
| 783 |
-
"language_model.model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-
|
| 784 |
-
"language_model.model.layers.26.mlp.down_proj.weight.quant_map": "model-
|
| 785 |
-
"language_model.model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 786 |
-
"language_model.model.layers.26.mlp.gate_proj.weight": "model-
|
| 787 |
-
"language_model.model.layers.26.mlp.gate_proj.weight.absmax": "model-
|
| 788 |
-
"language_model.model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-
|
| 789 |
-
"language_model.model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 790 |
-
"language_model.model.layers.26.mlp.gate_proj.weight.quant_map": "model-
|
| 791 |
-
"language_model.model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 792 |
-
"language_model.model.layers.26.mlp.up_proj.weight": "model-
|
| 793 |
-
"language_model.model.layers.26.mlp.up_proj.weight.absmax": "model-
|
| 794 |
-
"language_model.model.layers.26.mlp.up_proj.weight.nested_absmax": "model-
|
| 795 |
-
"language_model.model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-
|
| 796 |
-
"language_model.model.layers.26.mlp.up_proj.weight.quant_map": "model-
|
| 797 |
-
"language_model.model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 798 |
-
"language_model.model.layers.26.post_attention_layernorm.weight": "model-
|
| 799 |
-
"language_model.model.layers.26.post_feedforward_layernorm.weight": "model-
|
| 800 |
-
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-
|
| 801 |
-
"language_model.model.layers.26.self_attn.k_norm.weight": "model-
|
| 802 |
-
"language_model.model.layers.26.self_attn.k_proj.weight": "model-
|
| 803 |
-
"language_model.model.layers.26.self_attn.k_proj.weight.absmax": "model-
|
| 804 |
-
"language_model.model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-
|
| 805 |
-
"language_model.model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 806 |
-
"language_model.model.layers.26.self_attn.k_proj.weight.quant_map": "model-
|
| 807 |
-
"language_model.model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 808 |
-
"language_model.model.layers.26.self_attn.o_proj.weight": "model-
|
| 809 |
-
"language_model.model.layers.26.self_attn.o_proj.weight.absmax": "model-
|
| 810 |
-
"language_model.model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-
|
| 811 |
-
"language_model.model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 812 |
-
"language_model.model.layers.26.self_attn.o_proj.weight.quant_map": "model-
|
| 813 |
-
"language_model.model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 814 |
-
"language_model.model.layers.26.self_attn.q_norm.weight": "model-
|
| 815 |
-
"language_model.model.layers.26.self_attn.q_proj.weight": "model-
|
| 816 |
-
"language_model.model.layers.26.self_attn.q_proj.weight.absmax": "model-
|
| 817 |
-
"language_model.model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-
|
| 818 |
-
"language_model.model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 819 |
-
"language_model.model.layers.26.self_attn.q_proj.weight.quant_map": "model-
|
| 820 |
-
"language_model.model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 821 |
-
"language_model.model.layers.26.self_attn.v_proj.weight": "model-
|
| 822 |
-
"language_model.model.layers.26.self_attn.v_proj.weight.absmax": "model-
|
| 823 |
-
"language_model.model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-
|
| 824 |
-
"language_model.model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 825 |
-
"language_model.model.layers.26.self_attn.v_proj.weight.quant_map": "model-
|
| 826 |
-
"language_model.model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 827 |
-
"language_model.model.layers.27.input_layernorm.weight": "model-
|
| 828 |
-
"language_model.model.layers.27.mlp.down_proj.weight": "model-
|
| 829 |
-
"language_model.model.layers.27.mlp.down_proj.weight.absmax": "model-
|
| 830 |
-
"language_model.model.layers.27.mlp.down_proj.weight.nested_absmax": "model-
|
| 831 |
-
"language_model.model.layers.27.mlp.down_proj.weight.nested_quant_map": "model-
|
| 832 |
-
"language_model.model.layers.27.mlp.down_proj.weight.quant_map": "model-
|
| 833 |
-
"language_model.model.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 834 |
-
"language_model.model.layers.27.mlp.gate_proj.weight": "model-
|
| 835 |
-
"language_model.model.layers.27.mlp.gate_proj.weight.absmax": "model-
|
| 836 |
-
"language_model.model.layers.27.mlp.gate_proj.weight.nested_absmax": "model-
|
| 837 |
-
"language_model.model.layers.27.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 838 |
-
"language_model.model.layers.27.mlp.gate_proj.weight.quant_map": "model-
|
| 839 |
-
"language_model.model.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 840 |
-
"language_model.model.layers.27.mlp.up_proj.weight": "model-
|
| 841 |
-
"language_model.model.layers.27.mlp.up_proj.weight.absmax": "model-
|
| 842 |
-
"language_model.model.layers.27.mlp.up_proj.weight.nested_absmax": "model-
|
| 843 |
-
"language_model.model.layers.27.mlp.up_proj.weight.nested_quant_map": "model-
|
| 844 |
-
"language_model.model.layers.27.mlp.up_proj.weight.quant_map": "model-
|
| 845 |
-
"language_model.model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 846 |
-
"language_model.model.layers.27.post_attention_layernorm.weight": "model-
|
| 847 |
-
"language_model.model.layers.27.post_feedforward_layernorm.weight": "model-
|
| 848 |
-
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-
|
| 849 |
-
"language_model.model.layers.27.self_attn.k_norm.weight": "model-
|
| 850 |
-
"language_model.model.layers.27.self_attn.k_proj.weight": "model-
|
| 851 |
-
"language_model.model.layers.27.self_attn.k_proj.weight.absmax": "model-
|
| 852 |
-
"language_model.model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-
|
| 853 |
-
"language_model.model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 854 |
-
"language_model.model.layers.27.self_attn.k_proj.weight.quant_map": "model-
|
| 855 |
-
"language_model.model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 856 |
-
"language_model.model.layers.27.self_attn.o_proj.weight": "model-
|
| 857 |
-
"language_model.model.layers.27.self_attn.o_proj.weight.absmax": "model-
|
| 858 |
-
"language_model.model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-
|
| 859 |
-
"language_model.model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 860 |
-
"language_model.model.layers.27.self_attn.o_proj.weight.quant_map": "model-
|
| 861 |
-
"language_model.model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 862 |
-
"language_model.model.layers.27.self_attn.q_norm.weight": "model-
|
| 863 |
-
"language_model.model.layers.27.self_attn.q_proj.weight": "model-
|
| 864 |
-
"language_model.model.layers.27.self_attn.q_proj.weight.absmax": "model-
|
| 865 |
-
"language_model.model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-
|
| 866 |
-
"language_model.model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 867 |
-
"language_model.model.layers.27.self_attn.q_proj.weight.quant_map": "model-
|
| 868 |
-
"language_model.model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 869 |
-
"language_model.model.layers.27.self_attn.v_proj.weight": "model-
|
| 870 |
-
"language_model.model.layers.27.self_attn.v_proj.weight.absmax": "model-
|
| 871 |
-
"language_model.model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-
|
| 872 |
-
"language_model.model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 873 |
-
"language_model.model.layers.27.self_attn.v_proj.weight.quant_map": "model-
|
| 874 |
-
"language_model.model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 875 |
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 876 |
"language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 877 |
"language_model.model.layers.28.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
|
|
@@ -879,12 +844,12 @@
|
|
| 879 |
"language_model.model.layers.28.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
|
| 880 |
"language_model.model.layers.28.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
|
| 881 |
"language_model.model.layers.28.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
|
| 882 |
-
"language_model.model.layers.28.mlp.gate_proj.weight": "model-
|
| 883 |
-
"language_model.model.layers.28.mlp.gate_proj.weight.absmax": "model-
|
| 884 |
-
"language_model.model.layers.28.mlp.gate_proj.weight.nested_absmax": "model-
|
| 885 |
-
"language_model.model.layers.28.mlp.gate_proj.weight.nested_quant_map": "model-
|
| 886 |
-
"language_model.model.layers.28.mlp.gate_proj.weight.quant_map": "model-
|
| 887 |
-
"language_model.model.layers.28.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 888 |
"language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 889 |
"language_model.model.layers.28.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
|
| 890 |
"language_model.model.layers.28.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
|
|
@@ -894,32 +859,32 @@
|
|
| 894 |
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 895 |
"language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 896 |
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 897 |
-
"language_model.model.layers.28.self_attn.k_norm.weight": "model-
|
| 898 |
-
"language_model.model.layers.28.self_attn.k_proj.weight": "model-
|
| 899 |
-
"language_model.model.layers.28.self_attn.k_proj.weight.absmax": "model-
|
| 900 |
-
"language_model.model.layers.28.self_attn.k_proj.weight.nested_absmax": "model-
|
| 901 |
-
"language_model.model.layers.28.self_attn.k_proj.weight.nested_quant_map": "model-
|
| 902 |
-
"language_model.model.layers.28.self_attn.k_proj.weight.quant_map": "model-
|
| 903 |
-
"language_model.model.layers.28.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 904 |
-
"language_model.model.layers.28.self_attn.o_proj.weight": "model-
|
| 905 |
-
"language_model.model.layers.28.self_attn.o_proj.weight.absmax": "model-
|
| 906 |
-
"language_model.model.layers.28.self_attn.o_proj.weight.nested_absmax": "model-
|
| 907 |
-
"language_model.model.layers.28.self_attn.o_proj.weight.nested_quant_map": "model-
|
| 908 |
-
"language_model.model.layers.28.self_attn.o_proj.weight.quant_map": "model-
|
| 909 |
-
"language_model.model.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 910 |
-
"language_model.model.layers.28.self_attn.q_norm.weight": "model-
|
| 911 |
-
"language_model.model.layers.28.self_attn.q_proj.weight": "model-
|
| 912 |
-
"language_model.model.layers.28.self_attn.q_proj.weight.absmax": "model-
|
| 913 |
-
"language_model.model.layers.28.self_attn.q_proj.weight.nested_absmax": "model-
|
| 914 |
-
"language_model.model.layers.28.self_attn.q_proj.weight.nested_quant_map": "model-
|
| 915 |
-
"language_model.model.layers.28.self_attn.q_proj.weight.quant_map": "model-
|
| 916 |
-
"language_model.model.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 917 |
-
"language_model.model.layers.28.self_attn.v_proj.weight": "model-
|
| 918 |
-
"language_model.model.layers.28.self_attn.v_proj.weight.absmax": "model-
|
| 919 |
-
"language_model.model.layers.28.self_attn.v_proj.weight.nested_absmax": "model-
|
| 920 |
-
"language_model.model.layers.28.self_attn.v_proj.weight.nested_quant_map": "model-
|
| 921 |
-
"language_model.model.layers.28.self_attn.v_proj.weight.quant_map": "model-
|
| 922 |
-
"language_model.model.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-
|
| 923 |
"language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 924 |
"language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 925 |
"language_model.model.layers.29.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
|
|
@@ -1878,13 +1843,13 @@
|
|
| 1878 |
"language_model.model.layers.47.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
|
| 1879 |
"language_model.model.layers.47.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
|
| 1880 |
"language_model.model.layers.47.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
|
| 1881 |
-
"language_model.model.layers.5.input_layernorm.weight": "model-
|
| 1882 |
-
"language_model.model.layers.5.mlp.down_proj.weight": "model-
|
| 1883 |
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 1884 |
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 1885 |
-
"language_model.model.layers.5.post_attention_layernorm.weight": "model-
|
| 1886 |
-
"language_model.model.layers.5.post_feedforward_layernorm.weight": "model-
|
| 1887 |
-
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-
|
| 1888 |
"language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 1889 |
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1890 |
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
|
@@ -1893,17 +1858,17 @@
|
|
| 1893 |
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1894 |
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1895 |
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 1896 |
-
"language_model.model.layers.6.mlp.gate_proj.weight": "model-
|
| 1897 |
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 1898 |
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1899 |
"language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1900 |
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1901 |
-
"language_model.model.layers.6.self_attn.k_norm.weight": "model-
|
| 1902 |
-
"language_model.model.layers.6.self_attn.k_proj.weight": "model-
|
| 1903 |
-
"language_model.model.layers.6.self_attn.o_proj.weight": "model-
|
| 1904 |
-
"language_model.model.layers.6.self_attn.q_norm.weight": "model-
|
| 1905 |
-
"language_model.model.layers.6.self_attn.q_proj.weight": "model-
|
| 1906 |
-
"language_model.model.layers.6.self_attn.v_proj.weight": "model-
|
| 1907 |
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1908 |
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 1909 |
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
@@ -1926,10 +1891,30 @@
|
|
| 1926 |
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1927 |
"language_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 1928 |
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1929 |
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1930 |
"language_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 1931 |
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1932 |
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1933 |
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1934 |
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 1935 |
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 12189748992
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
|
|
|
| 54 |
"language_model.model.layers.0.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 55 |
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 56 |
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"language_model.model.layers.1.mlp.down_proj.weight.absmax": "model-00001-of-00003.safetensors",
|
| 58 |
+
"language_model.model.layers.1.mlp.down_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
|
| 59 |
+
"language_model.model.layers.1.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
|
| 60 |
+
"language_model.model.layers.1.mlp.down_proj.weight.quant_map": "model-00001-of-00003.safetensors",
|
| 61 |
+
"language_model.model.layers.1.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 62 |
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 63 |
+
"language_model.model.layers.1.mlp.gate_proj.weight.absmax": "model-00001-of-00003.safetensors",
|
| 64 |
+
"language_model.model.layers.1.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
|
| 65 |
+
"language_model.model.layers.1.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
|
| 66 |
+
"language_model.model.layers.1.mlp.gate_proj.weight.quant_map": "model-00001-of-00003.safetensors",
|
| 67 |
+
"language_model.model.layers.1.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 68 |
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"language_model.model.layers.1.mlp.up_proj.weight.absmax": "model-00001-of-00003.safetensors",
|
| 70 |
+
"language_model.model.layers.1.mlp.up_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
|
| 71 |
+
"language_model.model.layers.1.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
|
| 72 |
+
"language_model.model.layers.1.mlp.up_proj.weight.quant_map": "model-00001-of-00003.safetensors",
|
| 73 |
+
"language_model.model.layers.1.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 74 |
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 75 |
"language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 76 |
"language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
|
|
|
| 102 |
"language_model.model.layers.1.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 103 |
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 104 |
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"language_model.model.layers.10.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 106 |
+
"language_model.model.layers.10.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 107 |
+
"language_model.model.layers.10.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 108 |
+
"language_model.model.layers.10.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 109 |
+
"language_model.model.layers.10.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 110 |
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"language_model.model.layers.10.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 112 |
+
"language_model.model.layers.10.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 113 |
+
"language_model.model.layers.10.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 114 |
+
"language_model.model.layers.10.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 115 |
+
"language_model.model.layers.10.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 116 |
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 117 |
+
"language_model.model.layers.10.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 118 |
+
"language_model.model.layers.10.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 119 |
+
"language_model.model.layers.10.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 120 |
+
"language_model.model.layers.10.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 121 |
+
"language_model.model.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 122 |
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 123 |
"language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 124 |
"language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 157 |
"language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 158 |
"language_model.model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 159 |
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 161 |
"language_model.model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 162 |
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 163 |
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 164 |
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 165 |
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"language_model.model.layers.12.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 167 |
+
"language_model.model.layers.12.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 168 |
+
"language_model.model.layers.12.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 169 |
+
"language_model.model.layers.12.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 170 |
+
"language_model.model.layers.12.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 171 |
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"language_model.model.layers.12.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 173 |
+
"language_model.model.layers.12.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 174 |
+
"language_model.model.layers.12.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 175 |
+
"language_model.model.layers.12.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 176 |
+
"language_model.model.layers.12.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 177 |
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"language_model.model.layers.12.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 179 |
+
"language_model.model.layers.12.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 180 |
+
"language_model.model.layers.12.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 181 |
+
"language_model.model.layers.12.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 182 |
+
"language_model.model.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 183 |
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 184 |
"language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 185 |
"language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 244 |
"language_model.model.layers.13.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 245 |
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 246 |
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"language_model.model.layers.14.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 248 |
+
"language_model.model.layers.14.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 249 |
+
"language_model.model.layers.14.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 250 |
+
"language_model.model.layers.14.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 251 |
+
"language_model.model.layers.14.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 252 |
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 253 |
+
"language_model.model.layers.14.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 254 |
+
"language_model.model.layers.14.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 255 |
+
"language_model.model.layers.14.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 256 |
+
"language_model.model.layers.14.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 257 |
+
"language_model.model.layers.14.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 258 |
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"language_model.model.layers.14.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 260 |
+
"language_model.model.layers.14.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 261 |
+
"language_model.model.layers.14.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 262 |
+
"language_model.model.layers.14.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 263 |
+
"language_model.model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 264 |
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 265 |
"language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 266 |
"language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 267 |
"language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 268 |
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 269 |
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 270 |
"language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 271 |
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 272 |
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 273 |
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 274 |
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 275 |
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 276 |
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 277 |
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 278 |
"language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 279 |
"language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 305 |
"language_model.model.layers.15.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 306 |
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 307 |
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 308 |
+
"language_model.model.layers.16.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 309 |
+
"language_model.model.layers.16.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 310 |
+
"language_model.model.layers.16.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 311 |
+
"language_model.model.layers.16.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 312 |
+
"language_model.model.layers.16.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 313 |
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 314 |
+
"language_model.model.layers.16.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 315 |
+
"language_model.model.layers.16.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 316 |
+
"language_model.model.layers.16.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 317 |
+
"language_model.model.layers.16.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 318 |
+
"language_model.model.layers.16.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 319 |
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 320 |
+
"language_model.model.layers.16.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 321 |
+
"language_model.model.layers.16.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 322 |
+
"language_model.model.layers.16.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 323 |
+
"language_model.model.layers.16.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 324 |
+
"language_model.model.layers.16.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 325 |
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 326 |
"language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 327 |
"language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 353 |
"language_model.model.layers.16.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 354 |
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 355 |
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 356 |
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 357 |
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 358 |
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 359 |
"language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 360 |
"language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 408 |
"language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 409 |
"language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 410 |
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 411 |
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 412 |
"language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 413 |
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 414 |
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 415 |
"language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 416 |
"language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 417 |
"language_model.model.layers.19.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
|
|
|
| 436 |
"language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 437 |
"language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 438 |
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 439 |
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 440 |
"language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 441 |
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 442 |
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 443 |
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 444 |
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 445 |
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
| 449 |
"language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 450 |
"language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 451 |
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 452 |
+
"language_model.model.layers.2.self_attn.k_proj.weight.absmax": "model-00001-of-00003.safetensors",
|
| 453 |
+
"language_model.model.layers.2.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
|
| 454 |
+
"language_model.model.layers.2.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
|
| 455 |
+
"language_model.model.layers.2.self_attn.k_proj.weight.quant_map": "model-00001-of-00003.safetensors",
|
| 456 |
+
"language_model.model.layers.2.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 457 |
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 458 |
+
"language_model.model.layers.2.self_attn.o_proj.weight.absmax": "model-00001-of-00003.safetensors",
|
| 459 |
+
"language_model.model.layers.2.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
|
| 460 |
+
"language_model.model.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
|
| 461 |
+
"language_model.model.layers.2.self_attn.o_proj.weight.quant_map": "model-00001-of-00003.safetensors",
|
| 462 |
+
"language_model.model.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 463 |
"language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 464 |
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 465 |
+
"language_model.model.layers.2.self_attn.q_proj.weight.absmax": "model-00001-of-00003.safetensors",
|
| 466 |
+
"language_model.model.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
|
| 467 |
+
"language_model.model.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
|
| 468 |
+
"language_model.model.layers.2.self_attn.q_proj.weight.quant_map": "model-00001-of-00003.safetensors",
|
| 469 |
+
"language_model.model.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 470 |
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 471 |
+
"language_model.model.layers.2.self_attn.v_proj.weight.absmax": "model-00001-of-00003.safetensors",
|
| 472 |
+
"language_model.model.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00003.safetensors",
|
| 473 |
+
"language_model.model.layers.2.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00003.safetensors",
|
| 474 |
+
"language_model.model.layers.2.self_attn.v_proj.weight.quant_map": "model-00001-of-00003.safetensors",
|
| 475 |
+
"language_model.model.layers.2.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00003.safetensors",
|
| 476 |
"language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 477 |
"language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 478 |
"language_model.model.layers.20.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
|
|
|
| 593 |
"language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 594 |
"language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 595 |
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 596 |
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 597 |
"language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 598 |
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 599 |
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 600 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 601 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 602 |
+
"language_model.model.layers.23.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 603 |
+
"language_model.model.layers.23.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 604 |
+
"language_model.model.layers.23.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 605 |
+
"language_model.model.layers.23.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 606 |
+
"language_model.model.layers.23.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 607 |
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 608 |
"language_model.model.layers.23.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 609 |
"language_model.model.layers.23.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 610 |
"language_model.model.layers.23.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 611 |
"language_model.model.layers.23.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 612 |
"language_model.model.layers.23.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 613 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 614 |
+
"language_model.model.layers.23.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 615 |
+
"language_model.model.layers.23.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 616 |
+
"language_model.model.layers.23.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 617 |
+
"language_model.model.layers.23.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 618 |
+
"language_model.model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 619 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 620 |
+
"language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 621 |
+
"language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 622 |
"language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 623 |
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 624 |
"language_model.model.layers.23.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
|
|
|
| 645 |
"language_model.model.layers.23.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 646 |
"language_model.model.layers.23.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 647 |
"language_model.model.layers.23.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 648 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 649 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 650 |
+
"language_model.model.layers.24.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 651 |
+
"language_model.model.layers.24.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 652 |
+
"language_model.model.layers.24.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 653 |
+
"language_model.model.layers.24.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 654 |
+
"language_model.model.layers.24.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 655 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 656 |
+
"language_model.model.layers.24.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 657 |
+
"language_model.model.layers.24.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 658 |
+
"language_model.model.layers.24.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 659 |
+
"language_model.model.layers.24.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 660 |
+
"language_model.model.layers.24.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 661 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 662 |
+
"language_model.model.layers.24.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 663 |
+
"language_model.model.layers.24.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 664 |
+
"language_model.model.layers.24.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 665 |
+
"language_model.model.layers.24.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 666 |
+
"language_model.model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 667 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 668 |
+
"language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 669 |
+
"language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 670 |
+
"language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 671 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 672 |
+
"language_model.model.layers.24.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 673 |
+
"language_model.model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 674 |
+
"language_model.model.layers.24.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 675 |
+
"language_model.model.layers.24.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 676 |
+
"language_model.model.layers.24.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 677 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 678 |
+
"language_model.model.layers.24.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 679 |
+
"language_model.model.layers.24.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 680 |
+
"language_model.model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 681 |
+
"language_model.model.layers.24.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 682 |
+
"language_model.model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 683 |
+
"language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 684 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 685 |
+
"language_model.model.layers.24.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 686 |
+
"language_model.model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 687 |
+
"language_model.model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 688 |
+
"language_model.model.layers.24.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 689 |
+
"language_model.model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 690 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 691 |
+
"language_model.model.layers.24.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 692 |
+
"language_model.model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 693 |
+
"language_model.model.layers.24.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 694 |
+
"language_model.model.layers.24.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 695 |
+
"language_model.model.layers.24.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 696 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 697 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 698 |
+
"language_model.model.layers.25.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 699 |
+
"language_model.model.layers.25.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 700 |
+
"language_model.model.layers.25.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 701 |
+
"language_model.model.layers.25.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 702 |
+
"language_model.model.layers.25.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 703 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 704 |
+
"language_model.model.layers.25.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 705 |
+
"language_model.model.layers.25.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 706 |
+
"language_model.model.layers.25.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 707 |
+
"language_model.model.layers.25.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 708 |
+
"language_model.model.layers.25.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 709 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 710 |
+
"language_model.model.layers.25.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 711 |
+
"language_model.model.layers.25.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 712 |
+
"language_model.model.layers.25.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 713 |
+
"language_model.model.layers.25.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 714 |
+
"language_model.model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 715 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 716 |
+
"language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 717 |
+
"language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 718 |
+
"language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 719 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 720 |
+
"language_model.model.layers.25.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 721 |
+
"language_model.model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 722 |
+
"language_model.model.layers.25.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 723 |
+
"language_model.model.layers.25.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 724 |
+
"language_model.model.layers.25.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 725 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 726 |
+
"language_model.model.layers.25.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 727 |
+
"language_model.model.layers.25.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 728 |
+
"language_model.model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 729 |
+
"language_model.model.layers.25.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 730 |
+
"language_model.model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 731 |
+
"language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 732 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 733 |
+
"language_model.model.layers.25.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 734 |
+
"language_model.model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 735 |
+
"language_model.model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 736 |
+
"language_model.model.layers.25.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 737 |
+
"language_model.model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 738 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 739 |
+
"language_model.model.layers.25.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 740 |
+
"language_model.model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 741 |
+
"language_model.model.layers.25.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 742 |
+
"language_model.model.layers.25.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 743 |
+
"language_model.model.layers.25.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 744 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 745 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 746 |
+
"language_model.model.layers.26.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 747 |
+
"language_model.model.layers.26.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 748 |
+
"language_model.model.layers.26.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 749 |
+
"language_model.model.layers.26.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 750 |
+
"language_model.model.layers.26.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 751 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"language_model.model.layers.26.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 753 |
+
"language_model.model.layers.26.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 754 |
+
"language_model.model.layers.26.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 755 |
+
"language_model.model.layers.26.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 756 |
+
"language_model.model.layers.26.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 757 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"language_model.model.layers.26.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 759 |
+
"language_model.model.layers.26.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 760 |
+
"language_model.model.layers.26.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 761 |
+
"language_model.model.layers.26.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 762 |
+
"language_model.model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 763 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 765 |
+
"language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 767 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"language_model.model.layers.26.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 769 |
+
"language_model.model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 770 |
+
"language_model.model.layers.26.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 771 |
+
"language_model.model.layers.26.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 772 |
+
"language_model.model.layers.26.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 773 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"language_model.model.layers.26.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 775 |
+
"language_model.model.layers.26.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 776 |
+
"language_model.model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 777 |
+
"language_model.model.layers.26.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 778 |
+
"language_model.model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 779 |
+
"language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 781 |
+
"language_model.model.layers.26.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 782 |
+
"language_model.model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 783 |
+
"language_model.model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 784 |
+
"language_model.model.layers.26.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 785 |
+
"language_model.model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 786 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 787 |
+
"language_model.model.layers.26.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 788 |
+
"language_model.model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 789 |
+
"language_model.model.layers.26.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 790 |
+
"language_model.model.layers.26.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 791 |
+
"language_model.model.layers.26.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 792 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 793 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"language_model.model.layers.27.mlp.down_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 795 |
+
"language_model.model.layers.27.mlp.down_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 796 |
+
"language_model.model.layers.27.mlp.down_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 797 |
+
"language_model.model.layers.27.mlp.down_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 798 |
+
"language_model.model.layers.27.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 799 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"language_model.model.layers.27.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 801 |
+
"language_model.model.layers.27.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 802 |
+
"language_model.model.layers.27.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 803 |
+
"language_model.model.layers.27.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 804 |
+
"language_model.model.layers.27.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 805 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"language_model.model.layers.27.mlp.up_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 807 |
+
"language_model.model.layers.27.mlp.up_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 808 |
+
"language_model.model.layers.27.mlp.up_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 809 |
+
"language_model.model.layers.27.mlp.up_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 810 |
+
"language_model.model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 811 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 813 |
+
"language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 815 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"language_model.model.layers.27.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 817 |
+
"language_model.model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 818 |
+
"language_model.model.layers.27.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 819 |
+
"language_model.model.layers.27.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 820 |
+
"language_model.model.layers.27.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 821 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"language_model.model.layers.27.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 823 |
+
"language_model.model.layers.27.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 824 |
+
"language_model.model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 825 |
+
"language_model.model.layers.27.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 826 |
+
"language_model.model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 827 |
+
"language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 828 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 829 |
+
"language_model.model.layers.27.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 830 |
+
"language_model.model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 831 |
+
"language_model.model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 832 |
+
"language_model.model.layers.27.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 833 |
+
"language_model.model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 834 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 835 |
+
"language_model.model.layers.27.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 836 |
+
"language_model.model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 837 |
+
"language_model.model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 838 |
+
"language_model.model.layers.27.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 839 |
+
"language_model.model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 840 |
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 841 |
"language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 842 |
"language_model.model.layers.28.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
|
|
|
|
| 844 |
"language_model.model.layers.28.mlp.down_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
|
| 845 |
"language_model.model.layers.28.mlp.down_proj.weight.quant_map": "model-00003-of-00003.safetensors",
|
| 846 |
"language_model.model.layers.28.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
|
| 847 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 848 |
+
"language_model.model.layers.28.mlp.gate_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 849 |
+
"language_model.model.layers.28.mlp.gate_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 850 |
+
"language_model.model.layers.28.mlp.gate_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 851 |
+
"language_model.model.layers.28.mlp.gate_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 852 |
+
"language_model.model.layers.28.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 853 |
"language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 854 |
"language_model.model.layers.28.mlp.up_proj.weight.absmax": "model-00003-of-00003.safetensors",
|
| 855 |
"language_model.model.layers.28.mlp.up_proj.weight.nested_absmax": "model-00003-of-00003.safetensors",
|
|
|
|
| 859 |
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 860 |
"language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 861 |
"language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 862 |
+
"language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 863 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 864 |
+
"language_model.model.layers.28.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 865 |
+
"language_model.model.layers.28.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 866 |
+
"language_model.model.layers.28.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 867 |
+
"language_model.model.layers.28.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 868 |
+
"language_model.model.layers.28.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 869 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 870 |
+
"language_model.model.layers.28.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 871 |
+
"language_model.model.layers.28.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 872 |
+
"language_model.model.layers.28.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 873 |
+
"language_model.model.layers.28.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 874 |
+
"language_model.model.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 875 |
+
"language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 876 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 877 |
+
"language_model.model.layers.28.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 878 |
+
"language_model.model.layers.28.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 879 |
+
"language_model.model.layers.28.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 880 |
+
"language_model.model.layers.28.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 881 |
+
"language_model.model.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 882 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 883 |
+
"language_model.model.layers.28.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 884 |
+
"language_model.model.layers.28.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 885 |
+
"language_model.model.layers.28.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 886 |
+
"language_model.model.layers.28.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 887 |
+
"language_model.model.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 888 |
"language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 889 |
"language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 890 |
"language_model.model.layers.29.mlp.down_proj.weight.absmax": "model-00003-of-00003.safetensors",
|
|
|
|
| 1843 |
"language_model.model.layers.47.self_attn.v_proj.weight.nested_quant_map": "model-00003-of-00003.safetensors",
|
| 1844 |
"language_model.model.layers.47.self_attn.v_proj.weight.quant_map": "model-00003-of-00003.safetensors",
|
| 1845 |
"language_model.model.layers.47.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00003-of-00003.safetensors",
|
| 1846 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 1847 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 1848 |
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 1849 |
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 1850 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 1851 |
+
"language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 1852 |
+
"language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 1853 |
"language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 1854 |
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1855 |
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
|
|
|
| 1858 |
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1859 |
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1860 |
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 1861 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 1862 |
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 1863 |
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1864 |
"language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1865 |
"language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1866 |
+
"language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
|
| 1867 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 1868 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 1869 |
+
"language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
|
| 1870 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 1871 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 1872 |
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1873 |
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 1874 |
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 1891 |
"language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1892 |
"language_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
|
| 1893 |
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 1894 |
+
"language_model.model.layers.8.self_attn.k_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 1895 |
+
"language_model.model.layers.8.self_attn.k_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 1896 |
+
"language_model.model.layers.8.self_attn.k_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 1897 |
+
"language_model.model.layers.8.self_attn.k_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 1898 |
+
"language_model.model.layers.8.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 1899 |
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 1900 |
+
"language_model.model.layers.8.self_attn.o_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 1901 |
+
"language_model.model.layers.8.self_attn.o_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 1902 |
+
"language_model.model.layers.8.self_attn.o_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 1903 |
+
"language_model.model.layers.8.self_attn.o_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 1904 |
+
"language_model.model.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 1905 |
"language_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
|
| 1906 |
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 1907 |
+
"language_model.model.layers.8.self_attn.q_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 1908 |
+
"language_model.model.layers.8.self_attn.q_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 1909 |
+
"language_model.model.layers.8.self_attn.q_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 1910 |
+
"language_model.model.layers.8.self_attn.q_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 1911 |
+
"language_model.model.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 1912 |
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 1913 |
+
"language_model.model.layers.8.self_attn.v_proj.weight.absmax": "model-00002-of-00003.safetensors",
|
| 1914 |
+
"language_model.model.layers.8.self_attn.v_proj.weight.nested_absmax": "model-00002-of-00003.safetensors",
|
| 1915 |
+
"language_model.model.layers.8.self_attn.v_proj.weight.nested_quant_map": "model-00002-of-00003.safetensors",
|
| 1916 |
+
"language_model.model.layers.8.self_attn.v_proj.weight.quant_map": "model-00002-of-00003.safetensors",
|
| 1917 |
+
"language_model.model.layers.8.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00002-of-00003.safetensors",
|
| 1918 |
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 1919 |
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 1920 |
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
tokenizer_config.json
CHANGED
|
@@ -51325,7 +51325,6 @@
|
|
| 51325 |
},
|
| 51326 |
"boi_token": "<start_of_image>",
|
| 51327 |
"bos_token": "<bos>",
|
| 51328 |
-
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n",
|
| 51329 |
"clean_up_tokenization_spaces": false,
|
| 51330 |
"eoi_token": "<end_of_image>",
|
| 51331 |
"eos_token": "<end_of_turn>",
|
|
|
|
| 51325 |
},
|
| 51326 |
"boi_token": "<start_of_image>",
|
| 51327 |
"bos_token": "<bos>",
|
|
|
|
| 51328 |
"clean_up_tokenization_spaces": false,
|
| 51329 |
"eoi_token": "<end_of_image>",
|
| 51330 |
"eos_token": "<end_of_turn>",
|