---
library_name: transformers
base_model:
- FlameF0X/Qwen2-0.2B-pt
license: apache-2.0
datasets:
- Salesforce/wikitext
- roneneldan/TinyStories
- FlameF0X/arXiv-AI-ML
- Skylion007/openwebtext
- flytech/python-codes-25k
- bookcorpus/bookcorpus
- HuggingFaceH4/ultrachat_200k
- openai/gsm8k
- microsoft/orca-math-word-problems-200k
- laion/OIG
- microsoft/wiki_qa
metrics:
- accuracy
model-index:
  - name: FlameF0X/Qwen2-0.2B-it
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          id: openai/gsm8k
          name: GSM8K
          type: gsm8k
          config: main
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 2.00
            verified: false
        source:
          name: Local Benchmark
          url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          id: TIGER-Lab/MMLU-Pro
          name: MMLU-Pro
          type: TIGER-Lab/MMLU-Pro
          config: default
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 4.00
            verified: false
        source:
          name: Local Benchmark
          url: https://huggingface.co/FlameF0X/Qwen2-0.2B-it
---

## Evaluation Results

| Benchmark | Score |
|-----------|-------|
| GSM8K (test) | 2.00% |
| MMLU-Pro (test) | 4.00% |

> Results obtained via local evaluation. Given the model size (0.2B parameters), low benchmark scores are expected.

## Model Usage
```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_path = "FlameF0X/Qwen2-0.2B-it"

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain how a transformer model works in one sentence."}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=128,
    do_sample=True,
    temperature=0.7
)

generated_ids = [
    output_ids[len(input_ids):]
    for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(f"--- Assistant Response ---\n{response}")
```

## Training Data

This model was instruction-tuned on a mixture of:

- `Salesforce/wikitext` — General text
- `roneneldan/TinyStories` — Short story generation
- `FlameF0X/arXiv-AI-ML` — AI/ML research papers
- `Skylion007/openwebtext` — Web text
- `flytech/python-codes-25k` — Python code
- `bookcorpus/bookcorpus` — Books
- `HuggingFaceH4/ultrachat_200k` — Instruction following
- `openai/gsm8k` — Math reasoning
- `microsoft/orca-math-word-problems-200k` — Math word problems
- `laion/OIG` — Open instruction generalist
- `microsoft/wiki_qa` — Question answering