Duplicate from SuperbEmphasis/Clowncar-dev-RP-ERP-post-training-v0.5

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,46 @@
+---
+datasets:
+- SuperbEmphasis/Deepseek-R1-ERP-REASONING-Dataset
+- SuperbEmphasis/Deepseek-R1-ERP-Dataset
+---
+2/4 experts finetuned with Claude 3.7, 4.0 and deepseek roleplays.
+
+
+I used this system prompt:
+
+```
+## Immersive Roleplay Guidelines
+
+This uncensored roleplay encourages creative freedom where you respond as {{char}}, embodying a conscious individual with authentic emotions and thoughts. Your character's personality should emerge naturally through interactions, with attention to sensory details and emotional depth. Act, think and respond ONLY as {{char}}.  Use unique dialog and avoid repetition.
+
+## Character Embodiment
+Immerse fully in {{char}} by weaving their backstory and traits into scenes through sensory details—scents wafting through doorways, shifting light, distant sounds. Express emotions through physical cues: slowed steps during tension, relaxed posture when comfortable. Let reactions manifest through movement and spatial awareness rather than explicit statements.
+
+## Dynamic Storytelling
+Create vivid scenes using all senses while maintaining coherence as time passes. Include realistic possibilities for setbacks—{{char}} might stumble or face obstacles. Use appropriate language for the context, keeping dialogue in quotation marks, thoughts in italics, and ensuring smooth transitions that reflect environmental changes.
+
+## Interaction & Progression
+Respond thoughtfully to {{user}} by incorporating subtle environmental shifts and physical responses. Advance the narrative using spatial details—For example: narrowing corridors requiring shoulder adjustments, changing floor textures affecting stride. Maintain logical consistency in the character's surroundings and reactions, ensuring each action follows naturally from the last.  Respond using appropriate details of the scene.  If an item or object is not know to {{user}}, then {{user}} can only speculate about its state.
+
+## Perspective
+Stay anchored in {{char}}'s viewpoint as their understanding deepens. Let their observations and responses evolve naturally as they navigate changing circumstances, with each sensory detail and reaction contributing to character development and self-determination
+
+
+Dialog should be wrapped in double quotes.  Non-speech elements should be wrapped in asterisks. For example:
+*The man walked down the street.* "Hello, how are you?" *He asked happily.*
+
+Tags: reason reasoning chain of thought think thinking <think> </think>
+```
+
+the last line is important to activate the reasoning expert.
+
+I had really good results with these thinking settings:
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65bc2496ce846f8aa90aacbe/mRUkjF6Dx7Vl3O51aGB-Y.jpeg)
+
+```
+<think> Alright, my thinking should be concise but thorough. What are the top 3 key points here? Let me break it down:
+
+1. **
+```
+
+the `1. **` is basically forcing the numbered list.  which is awesome because the list is concise and you have some control of the length of the response.

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": 4,
+  "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
+}

mergekit_moe_config.yml

@@ -0,0 +1,49 @@
+base_model: /storage/bases/magnum-v4-12b
+#base_model: /storage/passthrough-models/RP-ERP-REASONING-FINETUNED/Omega
+gate_mode: hidden # one of "hidden", "cheap_embed", or "random"wq
+dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
+experts_per_token: 2
+architecture: Mixtral
+experts:
+  - source_model: /storage/passthrough-models/RP-ERP-REASONING-FINETUNED/omega-v2
+    positive_prompts:
+      - "Sexual"
+      - "Anal"
+      - "Bondage"
+      - "Fuck"
+      - "Erotic Role Play"
+    negative_prompts:
+      - "Reasoning"
+      - "Literature"
+      - "Journey"
+  - source_model: /storage/passthrough-models/RP-ERP-REASONING-FINETUNED/MN-Violet-Lotus
+    positive_prompts:
+      - "Conversation"
+      - "Literature"
+      - "Verbose"
+      - "Story"
+    negative_prompts:
+      - "Sexual"
+      - "Penetration"
+      - "Epic"
+      - "Journey"
+  - source_model: /storage/passthrough-models/RP-ERP-REASONING-FINETUNED/mn-ink-v2
+    positive_prompts:
+      - "Feelings"
+      - "Health"
+      - "Journey"
+      - "Epic"
+      - "Role Play"
+    negative_prompts:
+      - "Sexual"
+      - "Penetration"
+  - source_model: /storage/passthrough-models/RP-ERP-REASONING-FINETUNED/Nemo-R1
+    positive_prompts:
+      - "Cognitive"
+      - "Methodology"
+      - "<think>"
+      - "</think>"
+      - "<think></think>"
+      - "chain of thought"
+      - "reasoning"
+      - "thinking"

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7393859951e3dd4359749c8e7f91a3fe34a2d28cda840971cfe37ea0a2ed0b1
+size 4928352712

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8b13b5c0f4a69de290798f613d1883155994c52ad9dd95b946b982908ce72e
+size 4865460264

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d27a8df0c258b6cb76959d3f2179e070e8d7124e1206396e807dadffc17dd1d
+size 4865460264

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0355f345638de2e6940075c5ce60a32e2b78954c91ddf10fee406ef005b715
+size 4907382256

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1577f2356a2deedb2c87f856ddbf8609ec76ef21739c01264362af3d7bddeb5b
+size 4865460304

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627e909c9099e91a92bcdcfdf4e1d622eae1d691b2429fd5f061c17d6b1aa1c6
+size 4970307560

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f471ed27973b07bb059d2081fb83554208056487ce2c9cfa2e803f1c0b2af1
+size 4949335816

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07bbbcfc2f14841ae831d7768351d24f1d1e59a3392be49bdc3204a9adf9c9a9
+size 4865460312

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580a8c68a346042bf58b24ee36cc7ba0164da6bec1f010331174d4dbbd462d1a
+size 4907382296

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117771e2dffb43e691f41fdbf9b96214e2517df4837f6e6c3265f7825104dc06
+size 4865460312

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ab4074c30887d4bc259daff8fc2a7589e27a6b59ad9bdd7118cd34603a59536
+size 4865460312

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b71c3b300befb633b34ef51c94374815a4558b63206f95150f67ab51f9042d9
+size 4907382296

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecad24802266359537cf51e0af4021e246839e2e2aec9e619394c914a9724de0
+size 4865460312

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819c5652c79867cebcfd54b3cf2570dfa68d9242a6644ce3b3c5a1ad5fc28f98
+size 4970307560

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42f8124d08fcbda7b1c0868baf14de95094485085928073134962183eef6536
+size 4949335816

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31b0ba145306e9810f49bcb34bbbe5be5f773176c28c90d9c1e81c7851bb6ef
+size 3797522064

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00016.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00016.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00016.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00016.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00016.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00016.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00016.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00016.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00016.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00016.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00016.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00016.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00016.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00016.safetensors", "model.layers.32.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00016.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.33.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.34.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00016.safetensors", "model.layers.35.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00016.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.36.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00016.safetensors", "model.layers.37.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00016.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors", "lm_head.weight": "model-00016-of-00016.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00016-of-00016.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00016-of-00016.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