Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS][" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST]" + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
+        {{- "[TOOL_CALLS][" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- message["content"] + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS]{"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "vocab_size": 131072
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eeb0a11c67d762d1877679f237520c16c4bb29cda59c28479eb97523b3c1682
+size 4991309496

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43376d4715c42096cc293631112bacd312c3ffcd363fd1af8a5a89ea29da1760
+size 4928417048

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c48e9999ffd9ea248dadd519eac1d1abeb4322ec3c25851a628d693e6fea2c
+size 4928417080

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a65a8b03ea444f9072c08bcd18d0521515064ba40e2f5ceb65a3cdb7014f096
+size 4928417104

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab5b65903e0aa80c15be07a2e537ffe4e686041c97c7b6ebda5a3d052b015b
+size 4928417104

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ead4f37763b5ea5d75716122c10f4735b047583f054ed6c62095d01368cbfa5
+size 4928417104

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbb09904ca220a2123e33d8a3207331d679dd610c03dd406a0a65a683ff5dde
+size 4928417104

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca639a89a44dbc77c8a012645fdf3ccacb23395852f34f7aa6a816dd4ce4784
+size 4928417104

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d27eb740e5dfceefa85634715105ce57ca253967f2a41e4b3d0dfbe09cb32b
+size 2622296688

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.safetensors", "lm_head.weight": "model-00009-of-00009.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a046b64b5eda8178d73f3a3b5c9ff1278e6c55b2ff2628dc20bee39b3371ab7
+size 17078444