Instructions to use AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B-GPTQ-Int4 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B-GPTQ-Int4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download post_config.json from AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B-GPTQ-Int4: direct link, hf CLI and curl.
- Browser
- Download file 277 Bytes
-
https://huggingface.co/AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B-GPTQ-Int4/resolve/main/post_config.json
- Command line
-
hf download hf://AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B-GPTQ-Int4/post_config.json
-
curl -L -o post_config.json https://huggingface.co/AXERA-TECH/DeepSeek-R1-Distill-Qwen-7B-GPTQ-Int4/resolve/main/post_config.json
277 Bytes
| { | |
| "enable_temperature" : true, | |
| "temperature" : 0.9, | |
| "enable_repetition_penalty" : false, | |
| "repetition_penalty" : 1.2, | |
| "penalty_window" : 20, | |
| "enable_top_p_sampling" : false, | |
| "top_p" : 0.8, | |
| "enable_top_k_sampling" : true, | |
| "top_k" : 10 | |
| } |