Instructions to use GavinChan1105/Llama-3-8B-ppo-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GavinChan1105/Llama-3-8B-ppo-lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GavinChan1105/Llama-3-8B-ppo-lora", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from GavinChan1105/Llama-3-8B-ppo-lora: direct link, hf CLI and curl.
- Browser
- Download file 462 Bytes
-
https://huggingface.co/GavinChan1105/Llama-3-8B-ppo-lora/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://GavinChan1105/Llama-3-8B-ppo-lora/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/GavinChan1105/Llama-3-8B-ppo-lora/resolve/main/special_tokens_map.json
462 Bytes
| { | |
| "bos_token": { | |
| "content": "<|begin_of_text|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "<|end_of_text|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<|reserved_special_token_0|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |