初始化项目，由ModelHub XC社区提供模型

Model: Lambent/Arsenic-Shahrazad-12B-v4.4.1-mtp
Source: Original Platform

.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 +1,61 @@
+---
+base_model: Lambent/Arsenic-Shahrazad-12B-v4.4
+library_name: transformers
+tags:
+- mistral
+- mistral-nemo
+- speculative-decoding
+- mtp
+- self-speculative
+- not-for-all-audiences
+license: cc-by-nc-4.0
+---
+
+Fork of llama.cpp to run the MTP head:
+https://github.com/lambentLogic/llama.cpp/tree/mtp-llama-mistral
+
+# Arsenic-Shahrazad-12B-v4.4.1-mtp
+
+A **co-adapted** variant of Arsenic-Shahrazad-12B-v4.4, trained alongside a Multi-Token-Prediction (MTP) draft head.
+
+The draft head was initially trained with the main model frozen, and then trained alongside the main model.
+
+This does increase speed slightly, especially at lower temperatures, but is mostly an exploration - likely not as effective as Qwen's yet.
+
+Usable as an ordinary chat model on its own; pair it with the MTP head GGUF for the speedup.
+
+## What "co-adapted" means here
+
+v4.4.1 was produced by training the base model (QLoRA, very low LR) and an MTP draft head together on her own temperature-1 self-generated samples — spanning creative writing, conversation, explanation, debate, poetry/constrained form, translation, and research, plus persona-conditioned variations for breadth.
+
+## Speedup (llama.cpp MTP speculative decoding)
+
+Draft acceptance and throughput vs. the initial v4.4 frozen-trunk MTP head, both Q5_K_M trunk + Q8 (T=0.4-baked) head, `n_max=1`, on in-distribution prompts:
+
+| temp | v4.4.1 accept | v4.4 head accept | v4.4.1 tok/s | v4.4 tok/s |
+|:----:|:-------------:|:----------------:|:------------:|:----------:|
+| 0.3  | **0.418**     | 0.373            | 81.5         | 75.5       |
+| 0.5  | **0.393**     | 0.360            | 75.6         | 73.9       |
+| 0.7  | **0.416**     | 0.371            | 76.8         | 74.1       |
+
+≈ +10% relative draft acceptance across the temperature range.
+
+Edit: After upstream improvements to MTP merged in, the tok/s have improved (calculated with the Q5_K_M model and Q8_0 head):
+
+| temp | draft accept | tok/s (MTP) | tok/s (no MTP) | speedup |
+|:----:|:------------:|:-----------:|:--------------:|:-------:|
+| 0.3  | 0.43         | 83.8        | 76.0           | **+10%** |
+| 0.5  | 0.42         | 82.3        | 74.6           | **+10%** |
+| 0.7  | 0.44         | 81.9        | 73.3           | **+12%** |
+
+## Usage
+
+### With MTP acceleration (llama.cpp)
+Requires the MTP draft-head GGUF and a llama.cpp build with `draft-mtp` support, not yet implemented:
+
+```bash
+llama-server -m Arsenic-Shahrazad-12B-v4.4.1-Q5_K_M.gguf \
+  --spec-type draft-mtp -md mtp-Arsenic-v4.4.1-T04-Q8_0.gguf \
+  --spec-draft-n-max 1 --spec-draft-p-min 0.0 \
+  -ngl 99 -c 8192
+```

chat_template.jinja

@@ -0,0 +1,121 @@
+{#- Default system message if no system prompt is passed. #}
+{%- set default_system_message = '' %}
+
+{#- Begin of sequence token. #}
+{{- bos_token }}
+
+{#- Handle system prompt if it exists. #}
+{#- System prompt supports text content or text chunks. #}
+{%- if messages[0]['role'] == 'system' %}
+    {{- '[SYSTEM_PROMPT]' -}}
+    {%- if messages[0]['content'] is string %}
+        {{- messages[0]['content'] -}}
+    {%- else %}        
+        {%- for block in messages[0]['content'] %}
+            {%- if block['type'] == 'text' %}
+                {{- block['text'] }}
+            {%- else %}
+                {{- raise_exception('Only text chunks are supported in system message contents.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+    {{- '[/SYSTEM_PROMPT]' -}}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+    {%- if default_system_message != '' %}
+        {{- '[SYSTEM_PROMPT]' + default_system_message + '[/SYSTEM_PROMPT]' }}
+    {%- endif %}
+{%- endif %}
+
+
+{#- Tools definition #}
+{%- set tools_definition = '' %}
+{%- set has_tools = false %}
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+    {%- set has_tools = true %}
+    {%- set tools_definition = '[AVAILABLE_TOOLS]' + (tools| tojson) + '[/AVAILABLE_TOOLS]' %}
+    {{- tools_definition }}
+{%- endif %}
+
+{#- Checks for alternating user/assistant messages. #}
+{%- set ns = namespace(index=0) %}
+{%- for message in loop_messages %}
+    {%- if message.role == 'user' or (message.role == 'assistant' and (message.tool_calls is not defined or message.tool_calls is none or message.tool_calls | length == 0)) %}
+        {%- if (message['role'] == 'user') != (ns.index % 2 == 0) %}
+            {{- raise_exception('After the optional system message, conversation roles must alternate user and assistant roles except for tool calls and results.') }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{#- Handle conversation messages. #}
+{%- for message in loop_messages %}
+
+    {#- User messages supports text content or text and image chunks. #}
+    {%- if message['role'] == 'user' %}
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- elif message['content'] | length > 0 %}
+            {{- '[INST]' }}
+            {%- if message['content'] | length == 2 %}
+                {%- set blocks = message['content'] | sort(attribute='type') %}
+            {%- else %}
+                {%- set blocks = message['content'] %}
+            {%- endif %}
+            {%- for block in blocks %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text, image and image_url chunks are supported in user message content.') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- else %}
+            {{- raise_exception('User message must have a string or a list of chunks in content') }}
+        {%- endif %}
+
+    {#- Assistant messages supports text content or text and image chunks. #}
+    {%- elif message['role'] == 'assistant' %}
+        {%- if (message['content'] is none or message['content'] == '' or message['content']|length == 0) and (message['tool_calls'] is not defined or message['tool_calls'] is none or message['tool_calls']|length == 0) %}
+            {{- raise_exception('Assistant message must have a string or a list of chunks in content or a list of tool calls.') }}
+        {%- endif %}
+
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- elif message['content'] | length > 0 %}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {{- block['text'] }}
+                {%- else %}
+                    {{- raise_exception('Only text chunks are supported in assistant message contents.') }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        
+        {%- if message['tool_calls'] is defined and message['tool_calls'] is not none and message['tool_calls']|length > 0 %}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson|safe %}
+                {%- elif arguments == '' %}
+                    {%- set arguments = '{}' %}
+                {%- endif %}
+                {{- '[TOOL_CALLS]' + tool['function']['name'] + '[ARGS]' + arguments }}
+            {%- endfor %}
+        {%- endif %}
+
+        {#- End of sequence token for each assistant messages. #}
+        {{- eos_token }}
+
+    {#- Tool messages only supports text content. #}
+    {%- elif message['role'] == 'tool' %}
+        {{- '[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]' }}
+
+    {#- Raise exception for unsupported roles. #}
+    {%- else %}
+        {{- raise_exception('Only user, assistant and tool roles are supported, got ' + message['role'] + '.') }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "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": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.2.0",
+  "unsloth_version": "2025.12.6",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 10,
+  "transformers_version": "5.2.0",
+  "use_cache": false
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0136c1864756ed2870802834d7094058ba705449a13b5e5cb5b640f42c0fff76
+size 4865489312

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f64a06a474e73cf31c50c450cab9bfc554dd52ca001e3ef0e46f1827a511dd
+size 4907529400

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b4542590053c3dc256b2d62a7098c7711a9da9266d3f582744373a67925366
+size 4907529464

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:330509a0cdf7e84e98779b7258c2e114b979bd1763a5c7dc60e02f1ce7a25dff
+size 4907529464

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b775d3dd1182e5f9e788bb43a6e52eb2b74245fed41ce08d4b3c77b6d91a3c
+size 4907529448

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_parameters": 12247782400,
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f2c686df49c26fb8af5d4fb464ec027f2439a09877988f89c67ff18e79fcdc
+size 17078306