初始化项目，由ModelHub XC社区提供模型
Model: FutureMa/Qwen3-8B-Drama-Thinking Source: Original Platform
This commit is contained in:
ModelHub XC
56
.gitattributes
vendored
Normal file
56
.gitattributes
vendored
Normal file
@@ -0,0 +1,56 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
354
README.md
Normal file
354
README.md
Normal file
@@ -0,0 +1,354 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: Qwen/Qwen3-8B
|
||||||
|
tags:
|
||||||
|
- qwen3
|
||||||
|
- thinking
|
||||||
|
- creative-writing
|
||||||
|
- screenwriting
|
||||||
|
- drama
|
||||||
|
- chain-of-thought
|
||||||
|
- reasoning
|
||||||
|
- ms-swift
|
||||||
|
- full-parameter-finetuning
|
||||||
|
datasets:
|
||||||
|
- custom-drama-thinking-dataset
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
- zh
|
||||||
|
library_name: transformers
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
model-index:
|
||||||
|
- name: Qwen3-8B-Drama-Thinking
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Creative Script Writing
|
||||||
|
metrics:
|
||||||
|
- type: thinking_depth
|
||||||
|
value: 9.0
|
||||||
|
name: Thinking Depth Score
|
||||||
|
- type: script_format
|
||||||
|
value: 9.0
|
||||||
|
name: Script Format Score
|
||||||
|
- type: dramatic_craft
|
||||||
|
value: 8.5
|
||||||
|
name: Dramatic Craft Score
|
||||||
|
---
|
||||||
|
|
||||||
|
# Qwen3-8B-Drama-Thinking
|
||||||
|
|
||||||
|
This model is a **full parameter fine-tuned** version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on a custom drama thinking dataset with explicit creative reasoning chains.
|
||||||
|
|
||||||
|
## Model Description
|
||||||
|
|
||||||
|
- **Base Model**: Qwen3-8B (8 billion parameters)
|
||||||
|
- **Training Method**: Full Parameter Fine-tuning (NOT LoRA)
|
||||||
|
- **Training Framework**: [ms-swift](https://github.com/modelscope/ms-swift)
|
||||||
|
- **Training Data**: Custom Drama Thinking Dataset (6,319 samples, avg ~5,000 tokens)
|
||||||
|
- **Specialization**: Screenwriting with explicit `<think>...</think>` creative reasoning
|
||||||
|
- **Hardware**: 2x NVIDIA H100 80GB SXM5
|
||||||
|
- **Training Time**: 2 hours 46 minutes (3 epochs)
|
||||||
|
- **Training Cost**: ~$17.86
|
||||||
|
|
||||||
|
## Key Features
|
||||||
|
|
||||||
|
### 🎬 Professional Screenwriting Assistant
|
||||||
|
|
||||||
|
This model generates dramatic scripts with **explicit creative deliberation**:
|
||||||
|
|
||||||
|
- ✅ **Thinking Process Visible**: Uses `<think>...</think>` tags to show internal reasoning
|
||||||
|
- ✅ **Deep Character Psychology**: Analyzes motivations, defense mechanisms, subtext
|
||||||
|
- ✅ **Structural Planning**: Three-act structure, emotional arcs, pacing decisions
|
||||||
|
- ✅ **Visual Storytelling**: Symbolism, atmosphere, cinematographic choices
|
||||||
|
- ✅ **Professional Format**: Correct screenplay formatting (scene headers, action lines, dialogue)
|
||||||
|
|
||||||
|
### 📊 Performance Comparison
|
||||||
|
|
||||||
|
Compared to base Qwen3-8B:
|
||||||
|
|
||||||
|
| Metric | Base Model | Fine-Tuned | Improvement |
|
||||||
|
|--------|------------|------------|-------------|
|
||||||
|
| **Output Length** | 1,071 tokens | 3,874 tokens | **+262%** |
|
||||||
|
| **Thinking Depth** | 5/10 | 9/10 | **+80%** |
|
||||||
|
| **Creative Reasoning** | 500 tokens | 3,400 tokens | **+580%** |
|
||||||
|
| **Craft Analysis** | Generic | Professional | **Qualitative leap** |
|
||||||
|
|
||||||
|
### 🎯 Unique Value Proposition
|
||||||
|
|
||||||
|
> This is not just a text generator - it's a **creative thinking partner** that externalizes
|
||||||
|
> the entire screenwriting process: from title analysis to character psychology to structural
|
||||||
|
> planning to final execution.
|
||||||
|
|
||||||
|
## Training Details
|
||||||
|
|
||||||
|
### Training Configuration
|
||||||
|
|
||||||
|
```bash
|
||||||
|
Model: Qwen/Qwen3-8B
|
||||||
|
Template: qwen3_thinking
|
||||||
|
Training Type: Full Parameter (all 8B parameters)
|
||||||
|
Max Length: 8192 tokens (for long thinking chains)
|
||||||
|
Batch Size: 1 per device × 2 GPUs
|
||||||
|
Gradient Accum: 8 steps (effective batch size: 16)
|
||||||
|
Learning Rate: 1e-5
|
||||||
|
Epochs: 3
|
||||||
|
Optimization: DeepSpeed Zero3 + Gradient Checkpointing
|
||||||
|
Liger Kernel, BF16 mixed precision
|
||||||
|
Loss Scale: ignore_empty_think
|
||||||
|
GPU Memory: ~74.62 GB per H100 (stable)
|
||||||
|
```
|
||||||
|
|
||||||
|
### Dataset Characteristics
|
||||||
|
|
||||||
|
- **Samples**: 6,319 dramatic script continuations
|
||||||
|
- **Average Length**: ~5,000 tokens per sample
|
||||||
|
- **Max Length**: ~6,100 tokens
|
||||||
|
- **Format**: Conversations with `<think>...</think>` reasoning tags
|
||||||
|
- **Content**:
|
||||||
|
- Script opening scenes (title, description, initial dialogue)
|
||||||
|
- Extensive creative deliberation (3,000+ tokens of thinking)
|
||||||
|
- Script continuation with proper formatting
|
||||||
|
- **Style**: Dramatic, emotionally intense scenarios (conflicts, reconciliation, tragedy)
|
||||||
|
|
||||||
|
### Training Metrics
|
||||||
|
|
||||||
|
- **Final Loss**: 0.844
|
||||||
|
- **Average Loss**: 0.978
|
||||||
|
- **Loss Trajectory**: 1.602 (start) → 0.82-0.83 (end)
|
||||||
|
- **Training Speed**: ~8 seconds/iteration
|
||||||
|
- **Total Steps**: 1,185
|
||||||
|
- **Checkpoints**: 5 saved (400, 800, 900, 1000, 1185)
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
### Quick Start (ms-swift)
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Install ms-swift
|
||||||
|
pip install ms-swift
|
||||||
|
|
||||||
|
# Inference (interactive mode)
|
||||||
|
swift infer \
|
||||||
|
--ckpt_dir FutureMa/Qwen3-8B-Drama-Thinking \
|
||||||
|
--template qwen3_thinking \
|
||||||
|
--max_new_tokens 4096 \
|
||||||
|
--temperature 0.7
|
||||||
|
```
|
||||||
|
|
||||||
|
### Python API
|
||||||
|
|
||||||
|
```python
|
||||||
|
import os
|
||||||
|
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
|
||||||
|
|
||||||
|
from swift.llm import PtEngine, InferRequest, RequestConfig
|
||||||
|
|
||||||
|
# Initialize engine
|
||||||
|
engine = PtEngine(
|
||||||
|
model_id_or_path="FutureMa/Qwen3-8B-Drama-Thinking",
|
||||||
|
max_batch_size=1,
|
||||||
|
torch_dtype="bfloat16"
|
||||||
|
)
|
||||||
|
|
||||||
|
# Create prompt
|
||||||
|
prompt = """Title: The Reunion
|
||||||
|
Description: Two estranged siblings meet at their childhood home after 20 years.
|
||||||
|
|
||||||
|
INT. FAMILY LIVING ROOM - DAY
|
||||||
|
|
||||||
|
SARAH (35) stands by the window, looking out at the garden.
|
||||||
|
MICHAEL (38) enters, hesitant."""
|
||||||
|
|
||||||
|
# Generate (streaming)
|
||||||
|
messages = [{'role': 'user', 'content': prompt}]
|
||||||
|
request = InferRequest(messages=messages)
|
||||||
|
config = RequestConfig(max_tokens=4096, temperature=0.7, stream=True)
|
||||||
|
|
||||||
|
for response in engine.infer([request], config)[0]:
|
||||||
|
if response:
|
||||||
|
print(response.choices[0].delta.content, end='', flush=True)
|
||||||
|
```
|
||||||
|
|
||||||
|
### Using with Transformers (requires adapting checkpoint)
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
"FutureMa/Qwen3-8B-Drama-Thinking",
|
||||||
|
torch_dtype="bfloat16",
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B")
|
||||||
|
|
||||||
|
messages = [
|
||||||
|
{"role": "system", "content": "You are a creative screenwriter assistant specialized in dramatic storytelling with internal reasoning."},
|
||||||
|
{"role": "user", "content": "Write a scene about forgiveness..."}
|
||||||
|
]
|
||||||
|
|
||||||
|
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||||
|
inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||||
|
|
||||||
|
outputs = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
|
||||||
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||||
|
```
|
||||||
|
|
||||||
|
## Example Output
|
||||||
|
|
||||||
|
**Input Prompt:**
|
||||||
|
```
|
||||||
|
Title: The Last Apology
|
||||||
|
Description: A daughter arrives at her estranged father's deathbed...
|
||||||
|
```
|
||||||
|
|
||||||
|
**Model Output** (excerpt):
|
||||||
|
```
|
||||||
|
<think>
|
||||||
|
Okay. Let's go. I'm sitting here with the opening of *The Last Apology* fresh in my mind,
|
||||||
|
and I need to figure out exactly where this goes next—not just the next scene, but the next
|
||||||
|
emotional beat, the next structural pivot...
|
||||||
|
|
||||||
|
First, the title: *The Last Apology*. That's not just poetic—it's structural. It tells me
|
||||||
|
this story is about delayed recognition, about the finality of words left unsaid...
|
||||||
|
|
||||||
|
[3,400 tokens of deep creative analysis including:]
|
||||||
|
- Title deconstruction and thematic implications
|
||||||
|
- Character psychology analysis
|
||||||
|
- Three-act structure planning
|
||||||
|
- Visual language and symbolism
|
||||||
|
- Multiple narrative paths considered
|
||||||
|
- Professional screenwriting techniques
|
||||||
|
</think>
|
||||||
|
|
||||||
|
INT. HOSPITAL ROOM - NIGHT
|
||||||
|
|
||||||
|
ANNA (28), in a wrinkled business suit, hesitates at the doorway.
|
||||||
|
|
||||||
|
DAVID (65) lies in bed, breathing labored...
|
||||||
|
|
||||||
|
[Script continues with proper formatting]
|
||||||
|
```
|
||||||
|
|
||||||
|
## Intended Use
|
||||||
|
|
||||||
|
### ✅ Recommended Use Cases
|
||||||
|
|
||||||
|
1. **Screenwriting Education**: Learn professional creative thinking process
|
||||||
|
2. **Script Ideation**: Generate story frameworks and narrative alternatives
|
||||||
|
3. **Story Consulting**: Explore "what if" scenarios with explicit reasoning
|
||||||
|
4. **Creative Brainstorming**: Understand decision-making in storytelling
|
||||||
|
5. **Draft Development**: Plan structure before execution
|
||||||
|
|
||||||
|
### ❌ Not Recommended For
|
||||||
|
|
||||||
|
1. **Final Shooting Scripts**: Requires human refinement for production
|
||||||
|
2. **Comedy/Action Genres**: Training bias toward dramatic content
|
||||||
|
3. **Long-form Series**: Single-pass generation may lack consistency
|
||||||
|
4. **Immediate Production**: Dialogue needs naturalization
|
||||||
|
|
||||||
|
## Evaluation Results
|
||||||
|
|
||||||
|
### Quantitative Metrics (vs. Base Model)
|
||||||
|
|
||||||
|
| Aspect | Score | Base Model | Improvement |
|
||||||
|
|--------|-------|------------|-------------|
|
||||||
|
| **Thinking Depth** | 9/10 | 5/10 | +80% |
|
||||||
|
| **Script Format** | 9/10 | 8/10 | +13% |
|
||||||
|
| **Dramatic Craft** | 8.5/10 | 8/10 | +6% |
|
||||||
|
| **Character Psychology** | 9/10 | 6/10 | +50% |
|
||||||
|
| **Decision Transparency** | 9/10 | 5/10 | +80% |
|
||||||
|
| **Overall** | 8.1/10 | 6.9/10 | +17% |
|
||||||
|
|
||||||
|
> **Note on Methodology:**
|
||||||
|
> *These metrics are generated using an **LLM-as-a-Judge** framework (Claude) comparing the fine-tuned model against the base model.
|
||||||
|
|
||||||
|
### Qualitative Improvements
|
||||||
|
|
||||||
|
- ✅ **Professional Voice**: Sounds like experienced screenwriter
|
||||||
|
- ✅ **Structural Thinking**: Explicit three-act planning
|
||||||
|
- ✅ **Meta-Awareness**: "This isn't just a script. It's a reckoning."
|
||||||
|
- ✅ **Non-Linear Reasoning**: Considers alternatives, backtracks, refines
|
||||||
|
- ✅ **Craft-Oriented**: Explains why choices serve the story
|
||||||
|
|
||||||
|
## Limitations
|
||||||
|
|
||||||
|
1. **Thinking Verbosity**: Generates ~3,400 tokens of thinking (87% of output)
|
||||||
|
- May be excessive for quick tasks
|
||||||
|
- Consider using `max_new_tokens` to limit length
|
||||||
|
|
||||||
|
2. **Incomplete Execution**: Token budget consumed by thinking
|
||||||
|
- Many planned scenes not fully generated
|
||||||
|
- May need 6,000-8,000 token limit for complete scripts
|
||||||
|
|
||||||
|
3. **Dialogue Naturalness**: More direct/literary than conversational
|
||||||
|
- Training data style influences output
|
||||||
|
- May need post-processing for natural speech
|
||||||
|
|
||||||
|
4. **Training Data Bias**: Skews toward melodramatic scenarios
|
||||||
|
- Less suited for subtle/realistic dialogue
|
||||||
|
- Best for emotionally intense stories
|
||||||
|
|
||||||
|
## Training Insights
|
||||||
|
|
||||||
|
### What Made This Successful
|
||||||
|
|
||||||
|
1. **8192 Token Context**: Essential for capturing full thinking chains
|
||||||
|
- Initial assumption of 2048 would have truncated data
|
||||||
|
- Average sample length: ~5,000 tokens
|
||||||
|
|
||||||
|
2. **DeepSpeed Zero3**: Required (not optional)
|
||||||
|
- Single H100: Would need ~109-114 GB (OOM)
|
||||||
|
- Zero3 sharding: ~74.62 GB per card ✅
|
||||||
|
|
||||||
|
3. **Full Parameter Training**: Worth the cost
|
||||||
|
- Deeper capability transfer than LoRA
|
||||||
|
- Better thinking process internalization
|
||||||
|
- Cost: $17.86 (2.8 hours) vs ~$5 for LoRA
|
||||||
|
|
||||||
|
4. **Quality Training Data**: 6,319 long-form reasoning examples
|
||||||
|
- Actual creative process in `<think>` tags
|
||||||
|
- High-quality dramatic writing
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{qwen3-drama-thinking-2025,
|
||||||
|
author = {FutureMa},
|
||||||
|
title = {Qwen3-8B-Drama-Thinking: Full Parameter Fine-tuning for Creative Screenwriting},
|
||||||
|
year = {2025},
|
||||||
|
publisher = {HuggingFace},
|
||||||
|
howpublished = {\url{https://huggingface.co/FutureMa/Qwen3-8B-Drama-Thinking}},
|
||||||
|
note = {Full parameter fine-tuning on 6,319 drama samples with explicit reasoning chains}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
## News & Updates
|
||||||
|
|
||||||
|
**[2025-12-23]** 🎉 **DramaBench Dataset is now open-source!** Evaluate your drama script generation with our comprehensive 6-dimensional benchmark framework (Format Standards, Narrative Efficiency, Character Consistency, Emotional Depth, Logic Consistency, Conflict Handling).
|
||||||
|
- 📊 Dataset: [FutureMa/DramaBench](https://huggingface.co/datasets/FutureMa/DramaBench)
|
||||||
|
- 📄 Paper: [arXiv:2512.19012](https://arxiv.org/abs/2512.19012)
|
||||||
|
- 🌐 Demo: [dramabench.pages.dev](https://dramabench.pages.dev/)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Acknowledgments
|
||||||
|
|
||||||
|
- **Base Model**: [Qwen Team](https://huggingface.co/Qwen) - Qwen3-8B
|
||||||
|
- **Training Framework**: [ms-swift](https://github.com/modelscope/ms-swift) - ModelScope SWIFT
|
||||||
|
- **Infrastructure**: [Lambda Cloud](https://lambdalabs.com/) - 2x H100 80GB SXM5
|
||||||
|
- **Dataset**: Custom Drama Thinking Dataset (6,319 samples)
|
||||||
|
|
||||||
|
## Model Card Contact
|
||||||
|
|
||||||
|
For questions or feedback:
|
||||||
|
- **HuggingFace**: [@FutureMa](https://huggingface.co/FutureMa)
|
||||||
|
- **GitHub Issues**: Report via ms-swift repository
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
**Training Date**: 2025-12-08
|
||||||
|
**Training Duration**: 2h 46m
|
||||||
|
**Model Size**: ~16GB (BF16 precision)
|
||||||
|
**Recommended VRAM**: 16GB+ for inference
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|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 loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and 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 %}
|
||||||
|
{%- 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 %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- 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' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\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 and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 12288,
|
||||||
|
"layer_types": [
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.57.3",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "4.57.3"
|
||||||
|
}
|
||||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5f60e26ff9187a86191977fe255865508da9ba5d8f84c7181b76673a38c32fa9
|
||||||
|
size 4902257696
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:372cc2f41d3805d0976cb2c4235ffced77133720f0cef420eacb1d3f975e9c13
|
||||||
|
size 4915960368
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c5d4596e6ad0c9c053e7e3a7f9efb1b55c1d48c9fea8a3719beb328af0df58b2
|
||||||
|
size 4983068496
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3acb42d50dbac0844e4f237dfe285ef618b93468fbe3d541c7f65d9dbc72ae5a
|
||||||
|
size 1580230264
|
||||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 308224,
|
||||||
|
"total_size": 16381470720
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151665": {
|
||||||
|
"content": "<tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151666": {
|
||||||
|
"content": "</tool_response>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151667": {
|
||||||
|
"content": "<think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151668": {
|
||||||
|
"content": "</think>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
1700
trainer_state.json
Normal file
1700
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d02cf2a49c614bff625160d51a72e2126e582e1938773da64ec29b678ba890ae
|
||||||
|
size 9553
|
||||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user