Instructions to use AXERA-TECH/Qwen2.5-7B-Instruct-GPTQ-Int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AXERA-TECH/Qwen2.5-7B-Instruct-GPTQ-Int4 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AXERA-TECH/Qwen2.5-7B-Instruct-GPTQ-Int4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.embed_tokens.weight.bfloat16.bin from AXERA-TECH/Qwen2.5-7B-Instruct-GPTQ-Int4: direct link, hf CLI and curl.
- Browser
- Download file 1.09 GB
-
https://huggingface.co/AXERA-TECH/Qwen2.5-7B-Instruct-GPTQ-Int4/resolve/main/model.embed_tokens.weight.bfloat16.bin
- Command line
-
hf download hf://AXERA-TECH/Qwen2.5-7B-Instruct-GPTQ-Int4/model.embed_tokens.weight.bfloat16.bin
-
curl -L -o model.embed_tokens.weight.bfloat16.bin https://huggingface.co/AXERA-TECH/Qwen2.5-7B-Instruct-GPTQ-Int4/resolve/main/model.embed_tokens.weight.bfloat16.bin
1.09 GB
- Xet hash:
- d74fc8148eb2664b03d65ac8086cff586ce827cd7b7077e8c61def19842a6a49
- Size of remote file:
- 1.09 GB
- SHA256:
- 78ae605b310cf526d54ba22b27796f44010fe28198cb6e3388efb62e09cc2ac4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.