Instructions to use fwtan/llama-1.1b-converted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fwtan/llama-1.1b-converted with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("fwtan/llama-1.1b-converted", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download act_dict.json from fwtan/llama-1.1b-converted: direct link, hf CLI and curl.
- Browser
- Download file 65.3 kB
-
https://huggingface.co/fwtan/llama-1.1b-converted/resolve/main/act_dict.json
- Command line
-
hf download hf://fwtan/llama-1.1b-converted/act_dict.json
-
curl -L -o act_dict.json https://huggingface.co/fwtan/llama-1.1b-converted/resolve/main/act_dict.json
65.3 kB
- Xet hash:
- 99245701e179cb905d2404a7bcd53d93c7547c75a68c1f972ea39cdd20dc5eec
- Size of remote file:
- 65.3 kB
- SHA256:
- 77029482067bdc31b8d36622eb92c4413f80a842d1875d862f572b3301def959
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.