Qwen3-8B-Drama-Thinking/README.md

---
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