初始化项目，由ModelHub XC社区提供模型

Model: ermiaazarkhalili/MiniCPM5-1B-SFT-Fable5
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model:
+  - openbmb/MiniCPM5-1B
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+  - unsloth
+  - lora
+  - trl
+  - sft
+---
+
+# MiniCPM5-1B-SFT-Fable5
+
+A LoRA fine-tune of [`openbmb/MiniCPM5-1B`](https://huggingface.co/openbmb/MiniCPM5-1B), supervised fine-tuned on `ermiaazarkhalili/Fable-5-Complete-2M-Clean` (private).
+
+| | |
+| --- | --- |
+| **Base model** | [`openbmb/MiniCPM5-1B`](https://huggingface.co/openbmb/MiniCPM5-1B) |
+| **Architecture** | `LlamaForCausalLM` |
+| **Parameters** | 1.1B |
+| **Training data** | `ermiaazarkhalili/Fable-5-Complete-2M-Clean` (private) |
+| **Method** | LoRA supervised fine-tuning via [Unsloth](https://github.com/unslothai/unsloth) + [TRL](https://github.com/huggingface/trl) |
+| **License** | `apache-2.0` (inherited from the base model) |
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "ermiaazarkhalili/MiniCPM5-1B-SFT-Fable5"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, dtype='auto', device_map='auto')
+
+messages = [{"role": "user", "content": "Explain gradient checkpointing in two sentences."}]
+inputs = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, return_tensors='pt'
+).to(model.device)
+
+outputs = model.generate(inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Training configuration
+
+| Setting | Value |
+| --- | --- |
+| LoRA rank (r) | 16 |
+| LoRA alpha | 16 |
+| Learning rate | 0.0002 |
+| Epochs | 1 |
+| Effective batch size | 8 (2 x 4 grad accum) |
+| Max sequence length | 4096 |
+| Base precision | 4-bit (QLoRA) |
+| Target modules | `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`, `out_proj` |
+
+## Observed training loss
+
+Measured from our SLURM logs for this configuration. These are training-loss
+observations only — no downstream benchmark evaluation has been run on this
+model, so they should not be read as a quality claim.
+
+| SLURM job | Steps | First loss | Final loss |
+| --- | --- | --- | --- |
+| `53234830` | 47,128 | 1.5772 | 1.3098 |
+
+## Limitations
+
+- No benchmark evaluation has been run on this checkpoint. The only reported
+  numbers are training-loss observations.
+- Inherits the biases, knowledge cutoff and failure modes of the base model.
+- Fine-tuned on a single instruction-following dataset; behaviour outside that
+  distribution is untested.
+- LoRA adapters were merged into the base weights, so the merged model cannot
+  be detached from this fine-tune.
+
+## Reproducing
+
+Trained by `notebooks/fable_distillation_minicpm5-1b_fable_unsloth.ipynb`, executed non-interactively with
+papermill on a SLURM H100 partition (Unsloth + TRL, LoRA).
+
+---
+
+*Card generated from the training run's own configuration and logs by*
+*`scripts/generate_hub_model_card.py`.*

chat_template.jinja

@@ -0,0 +1,179 @@
+{{- bos_token }}{%- if tools %}
+    {%- set tool_definitions %}
+        {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+        {%- for tool in tools %}
+            {{- "\n" }}
+            {{- tool | tojson(ensure_ascii=False) }}
+        {%- endfor %}
+        {{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
+    {%- endset %}
+    
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if '<tool_def_sep>' in messages[0].content %}
+            {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
+        {%- else %}
+            {{- messages[0].content + '\n\n' + tool_definitions }}
+        {%- endif %}
+    {%- else %}
+        {{- tool_definitions.lstrip() }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        
+        {%- if message.tool_calls %}
+            {%- set content_parts = content.split('<tool_sep>') %}
+            {%- set processed_content = content_parts[0] %}
+            {%- set tool_calls_count = message.tool_calls|length %}
+            {%- set tool_sep_count = content_parts|length - 1 %}
+            {%- set min_count = [tool_calls_count, tool_sep_count]|min %}
+            
+            {%- for i in range(1, content_parts|length) %}
+                {%- set tool_index = i - 1 %}
+                {%- if tool_index < tool_calls_count %}
+                    {%- set tool_call = message.tool_calls[tool_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set single_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
+                {%- else %}
+                    {%- set processed_content = processed_content + content_parts[i] %}
+                {%- endif %}
+            {%- endfor %}
+            
+            {%- if tool_calls_count > tool_sep_count %}
+                {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
+                    {%- set tool_call = message.tool_calls[remaining_index] %}
+                    {%- if tool_call.function %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {%- set remaining_tool_xml %}
+                        {{- '<function name="' ~ tool_call.name ~ '">' }}
+                        {%- if tool_call.arguments %}
+                            {%- set args_dict = tool_call.arguments %}
+                            {%- for param_name, param_value in args_dict.items() %}
+                                {{- '<param name="' ~ param_name ~ '">' }}
+                                {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                                    {{- '<![CDATA[' + param_value + ']]>' }}
+                                {%- else %}
+                                    {{- param_value }}
+                                {%- endif %}
+                                {{- '</param>' }}
+                            {%- endfor %}
+                        {%- endif %}
+                        {{- '</function>' }}
+                    {%- endset %}
+                    {%- set processed_content = processed_content + remaining_tool_xml %}
+                {%- endfor %}
+            {%- endif %}
+            
+            {%- set content = processed_content %}
+        {%- endif %}
+        
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if reasoning_content %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        
+        {%- if message.tool_calls and not has_tool_sep %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<function name="' ~ tool_call.name ~ '">' }}
+                {%- if tool_call.arguments %}
+                    {%- set args_dict = tool_call.arguments %}
+                    {%- for param_name, param_value in args_dict.items() %}
+                        {{- '<param name="' ~ param_name ~ '">' }}
+                        {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
+                            {{- '<![CDATA[' + param_value + ']]>' }}
+                        {%- else %}
+                            {{- param_value }}
+                        {%- endif %}
+                        {{- '</param>' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- content }}
+        {%- else %}
+            {{- message.content | tojson(ensure_ascii=False) }}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined %}
+        {%- if enable_thinking is false %}
+            {{- '<think>\n\n</think>\n\n' }}
+        {%- elif enable_thinking is true %}
+            {{- '<think>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,32 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 1,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 4608,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": 130559,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+        "rope_theta": 5000000,
+        "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "unsloth_version": "2026.4.6",
+    "use_cache": false,
+    "vocab_size": 130560
+}

model-00000-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6721565c376890f55ef4253fb50c7c707cef09da833902b5dd129ef805a17f93
+size 2161290912

model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 2161265664
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00000-of-00001.safetensors",
+    "lm_head.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00000-of-00001.safetensors",
+    "model.norm.weight": "model-00000-of-00001.safetensors"
+  }
+}