初始化项目，由ModelHub XC社区提供模型

Model: MrRikyz/FusionPulse-24B
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 +1,135 @@
+---
+base_model:
+- TheDrummer/Magidonia-24B-v4.3
+- Ateron/Sketch-Cydonia
+- OddTheGreat/Rotor_24B_V.1
+- DarkArtsForge/Magistaroth-24B-v1.1
+- MrRikyz/Rei-Pulse-24B
+- sophosympatheia/Magistry-24B-v1.0
+- TheDrummer/Cydonia-24B-v4.3
+library_name: transformers
+tags:
+- mergekit
+- merge
+- RP
+- NSFW
+- roleplay
+---
+<div style="width: 100%; text-align: center; margin-bottom: 20px;">
+  <h1 style="font-size: 2.5em; font-weight: bold; color: #4A90E2;">FusionPulse-24B</h1>
+  <hr style="border: 0; height: 1px; background: linear-gradient(to right, transparent, #4A90E2, transparent); margin: 20px 0;">
+</div>
+
+## 🌟 Overview
+
+**FusionPulse-24B** is a merge built on top of `Magidonia-24B-v4.3`. 
+
+The model uses the **TIES** method
+
+### 🧩 Models Merged
+
+This model results from a merge between:
+
+* **TheDrummer/Magidonia-24B-v4.3** (Base)
+* **Ateron/Sketch-Cydonia**
+* **OddTheGreat/Rotor_24B_V.1**
+* **DarkArtsForge/Magistaroth-24B-v1.1**
+* **MrRikyz/Rei-Pulse-24B**
+* **sophosympatheia/Magistry-24B-v1.0**
+* **TheDrummer/Cydonia-24B-v4.3**
+
+---
+
+## 🛠️ Merge Details
+
+### Method: TIES
+The merge was performed using `mergekit` with the following parameters:
+- **Base Model:** TheDrummer/Magidonia-24B-v4.3
+- **Dtype:** float32
+- **ODtype** BFloat16
+- **tokenizer source** base
+
+### ⚙️ Configuration
+<details>
+<summary><b>View Full Mergekit YAML</b></summary>
+
+```yaml
+base_model: TheDrummer/Magidonia-24B-v4.3
+dtype: float32
+merge_method: ties
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 40]
+        model: Ateron/Sketch-Cydonia
+        parameters:
+          density: 0.55
+          weight: 0.18
+      - layer_range: [0, 40]
+        model: OddTheGreat/Rotor_24B_V.1
+        parameters:
+          density: 0.65
+          weight: 0.22
+      - layer_range: [0, 40]
+        model: DarkArtsForge/Magistaroth-24B-v1.1
+        parameters:
+          density: 0.7
+          weight: 0.27
+      - layer_range: [0, 40]
+        model: MrRikyz/Rei-Pulse-24B
+        parameters:
+          density: 0.6
+          weight: 0.19
+      - layer_range: [0, 40]
+        model: sophosympatheia/Magistry-24B-v1.0
+        parameters:
+          density: 0.44
+          weight: 0.23
+      - layer_range: [0, 40]
+        model: TheDrummer/Cydonia-24B-v4.3
+        parameters:
+          density: 0.25
+          weight: 0.18
+      - layer_range: [0, 40]
+        model: TheDrummer/Magidonia-24B-v4.3
+
+base_model_alpha: 0.85
+
+ties:
+  merge_strategy: sum
+  normalize: true
+  sparsity: 0.17
+  rescale: true
+
+layer_wise:
+  - filter: "layers.0-8.*"
+    scale: 0.75
+  - filter: "layers.9-20.*"
+    scale: 1.05
+  - filter: "layers.21-31.*"
+    scale: 1.15
+
+tensor_factors:
+  attention: 1.1
+  mlp: 1.2
+
+post:
+  normalize: true
+  clamp: 2.5
+
+out_dtype: bfloat16
+tokenizer:
+  source: base
+```
+</details>
+
+# ✨ Acknowledgements
+
+Thanks to the authors of the original models for their incredible work:
+
+- Ateron for `Sketch-Cydonia`
+- OddTheGreat for `Rotor_24B_V.1`
+- DarkArtsForge for `Magistaroth-24B-v1.1`
+- sophosympatheia for `Magistry-24B-v1.0`
+- TheDrummer for `Cydonia-24B-v4.3` and `Magidonia-24B-v4.3`

chat_template.jinja

@@ -0,0 +1,112 @@
+{%- set default_system_message = 'First draft your thinking process (inner monologue) until you arrive at a response. Format your response using Markdown, and use LaTeX for any mathematical equations. Write both your thoughts and the response in the same language as the input.\n\nYour thinking process must follow the template below:[THINK]Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate the response. Use the same language as the input.[/THINK]Here, provide a self-contained response.' %}
+ 
+{{- bos_token }}
+ 
+{#- Extract system message if present -#}
+{%- if messages[0]['role'] == 'system' %}
+    {%- if messages[0]['content'] is string %}
+        {%- set raw_system_message = messages[0]['content'] %}
+    {%- else %}
+        {%- set raw_system_message = messages[0]['content'][0]['text'] %}
+    {%- endif %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set raw_system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+ 
+{#- Detect THINK flag by searching for exact phrase "/think" -#}
+{%- if "/think" in raw_system_message %}
+    {%- set THINK = True %}
+{%- else %}
+    {%- set THINK = False %}
+{%- endif %}
+ 
+{#- Apply logic depending on THINK flag -#}
+{%- if THINK %}
+    {%- if raw_system_message|length > 0 %}
+        {%- set system_message = default_system_message + "\n\n" + raw_system_message %}
+    {%- else %}
+        {%- set system_message = default_system_message %}
+    {%- endif %}
+    {{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
+{%- else %}
+    {%- if raw_system_message|length > 0 %}
+        {{- '[SYSTEM_PROMPT]' + raw_system_message + '[/SYSTEM_PROMPT]' }}
+    {%- endif %}
+{%- endif %}
+ 
+ 
+{#- Tool description appended ONLY to last user message. Edits made by Unsloth #}
+{%- set tools_description = "" %}
+{%- set has_tools = false %}
+ 
+{%- if tools is defined and tools is not none and tools|length > 0 %}
+    {%- set has_tools = true %}
+    {%- set tools_description = "[AVAILABLE_TOOLS]" + (tools | tojson) + "[/AVAILABLE_TOOLS]" %}
+    {{- tools_description }}
+{%- endif %}
+ 
+{%- for message in loop_messages %}
+    {%- if message['role'] == 'user' %}
+ 
+        {%- if message['content'] is string %}
+            {{- '[INST]' + message['content'] + '[/INST]' }}
+        {%- else %}
+            {{- '[INST]' }}
+            {%- for block in message['content'] %}
+                {%- if block['type'] == 'text' %}
+                    {%- if block['text'] is defined %}
+                        {{- block['text'] }}
+                    {%- else %}
+                        {{- block['content'] }}
+                    {%- endif %}
+                {%- elif block['type'] in ['image', 'image_url'] %}
+                    {{- '[IMG]' }}
+                {%- else %}
+                    {{- raise_exception('Only text and image blocks are supported in message content!') }}
+                {%- endif %}
+            {%- endfor %}
+            {{- '[/INST]' }}
+        {%- endif %}
+ 
+    {%- elif message['role'] == 'system' %}
+        {%- if message['content'] is string %}
+            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
+        {%- else %}
+            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
+        {%- endif %}
+ 
+    {%- elif message['role'] == 'assistant' %}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- elif message['content'] is iterable  %}
+            {{- message['content'][0]['text'] }}
+        {%- endif %}
+ 
+        {%- if message['tool_calls'] is defined and message['tool_calls'] is not none %}
+            {%- for tool in message['tool_calls'] %}
+                {%- set arguments = tool['function']['arguments'] %}
+                {%- if arguments is not string %}
+                    {%- set arguments = arguments|tojson %}
+                {%- endif %}
+                {{- "[TOOL_CALLS]" + tool['function']['name'] + "[ARGS]" + arguments }}
+            {%- endfor %}
+        {%- endif %}
+ 
+        {{- 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|string + "[/TOOL_RESULTS]" }}
+ 
+    {%- else %}
+        {{- raise_exception('Only user, system, assistant and tool roles are supported!') }}
+    {%- endif %}
+{%- endfor %}
+ 
+{#- Licensed under the Apache License, Version 2.0 (the "License") #}

config.json

@@ -0,0 +1,27 @@
+{
+  "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": 32768,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 11,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,69 @@
+base_model: TheDrummer/Magidonia-24B-v4.3
+dtype: float32
+merge_method: ties
+modules:
+  default:
+    slices:
+    - sources:
+      - layer_range: [0, 40]
+        model: Ateron/Sketch-Cydonia
+        parameters:
+          density: 0.55
+          weight: 0.18
+      - layer_range: [0, 40]
+        model: OddTheGreat/Rotor_24B_V.1
+        parameters:
+          density: 0.65
+          weight: 0.22
+      - layer_range: [0, 40]
+        model: DarkArtsForge/Magistaroth-24B-v1.1
+        parameters:
+          density: 0.7
+          weight: 0.27
+      - layer_range: [0, 40]
+        model: MrRikyz/Rei-Pulse-24B
+        parameters:
+          density: 0.6
+          weight: 0.19
+      - layer_range: [0, 40]
+        model: sophosympatheia/Magistry-24B-v1.0
+        parameters:
+          density: 0.44
+          weight: 0.23
+      - layer_range: [0, 40]
+        model: TheDrummer/Cydonia-24B-v4.3
+        parameters:
+          density: 0.25
+          weight: 0.18
+      - layer_range: [0, 40]
+        model: TheDrummer/Magidonia-24B-v4.3
+
+base_model_alpha: 0.85
+
+ties:
+  merge_strategy: sum
+  normalize: true
+  sparsity: 0.17
+  rescale: true
+
+layer_wise:
+  - filter: "layers.0-8.*"
+    scale: 0.75
+
+  - filter: "layers.9-20.*"
+    scale: 1.05
+
+  - filter: "layers.21-31.*"
+    scale: 1.15
+
+tensor_factors:
+  attention: 1.1
+  mlp: 1.2
+
+post:
+  normalize: true
+  clamp: 2.5
+
+out_dtype: bfloat16
+tokenizer:
+  source: base

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af47b1e80f69f03b663cf2b699098d1f65e8c32c9ba0088fc2d6c37a75dbf91
+size 4907389312

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99fd584feec4cad7e4e96f59d34a3309959dc265f0e65c7769584fe573bc420
+size 4781592832

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2363eb561d25a762f758cb616f305c37a30a8cdf9363bd91a9aff8cac8972c56
+size 4781592816

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b92a387cb99cb01f13620527e50f950edfd72e32283a6bd8deff0aaf37b9403
+size 4886471592

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:850a488866829077b595a7b25f0c2fc29a3672c9ec2fcafb6c69984df14454a4
+size 4781592832

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:837302dc5fd40e7fbbd8484675ee7ae697cd75a98a7f471633ba8ea12974e8b4
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f054b29c710d3e94f4e0a6e4795a91a418d60b846b1abac5dc7f46d73feab8
+size 4886471592

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142b09c70d9bda3a0ee63d7a5a91b4638a698b2eefaec657f68cbca8897161a7
+size 4781592832

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160b02f7e0f9f8b32f7e6ad8e7803bd71542181700f79abc67350cdc57ebcd31
+size 4781592800

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322e8fd60e0ca1a8d36e8c6412d68f0eb9f22305737b9ea917d0434caaff3e11
+size 3774959456

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 47144806400,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00010.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:158915c7c928301e0d32f1da363e45c294d907bd4c64a8e855f0bd1a47b9e870
+size 17078001