Downloads · 30 days
4
8% of all-time downloads
Qwen2.5-0.5B-Instruct-think-0701
doupari/Qwen2.5-0.5B-Instruct-think-0701
Qwen2.5-0.5B-Instruct-think-0701 is a text generation model from doupari. Use it when you need the model to write or continue text. It is set up for peft.
LoRA adapter fine-tuned from Qwen/Qwen2.5-0.5B-Instruct for the graph QA think extraction setting.
All-time downloads
52
Public
Repo size
46.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors35.2 MB · 69%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026
- SHA
- c51ba11f
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen2.5-0.5B-Instruct-think-0701
LoRA adapter fine-tuned from Qwen/Qwen2.5-0.5B-Instruct for the graph QA think extraction setting.
Checkpoint selection
Uploaded checkpoint: checkpoint-2094
This checkpoint was selected from:
/home/hyeseojeon/data/graph/outputs/finetune/Qwen2.5-0.5B-Instruct-think
Selection criterion: lowest eval loss found in trainer_state.json.
Best eval loss: 0.09406370669603348
Adapter config
- PEFT type: LoRA
- Rank: 16
- LoRA alpha: 32
- LoRA dropout: 0.05
- Base model:
Qwen/Qwen2.5-0.5B-Instruct
- Task
- Text Generation
- Library
- peft
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026