Views
No views yet
| Parameter | Specification |
|---|---|
| Base Architecture | Qwen2.5-1.5B-Instruct |
| Format | Merged FP16 (Full Precision) |
| File Size | ~3 GB (model.safetensors) |
| Dependencies | Standard transformers library (Native execution; no PEFT/LoRA required) |
1generation_config = {
2 "max_new_tokens": 512, # Adjust based on your needs
3 "min_new_tokens": 1,
4 "do_sample": True,
5 "temperature": 0.2, # Recommended range: 0.1 - 0.3 for precise responses
6 "top_p": 0.85,
7 "repetition_penalty": 1.15
8}