Instructions to use Ext-Sub/llama-7b_wizardlm_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Ext-Sub/llama-7b_wizardlm_lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/your/base/model/path") model = PeftModel.from_pretrained(base_model, "Ext-Sub/llama-7b_wizardlm_lora") - Notebooks
- Google Colab
- Kaggle
Download added_tokens.json from Ext-Sub/llama-7b_wizardlm_lora: direct link, hf CLI and curl.
- Browser
- Download file 21 Bytes
-
https://huggingface.co/Ext-Sub/llama-7b_wizardlm_lora/resolve/main/added_tokens.json
- Command line
-
hf download hf://Ext-Sub/llama-7b_wizardlm_lora/added_tokens.json
-
curl -L -o added_tokens.json https://huggingface.co/Ext-Sub/llama-7b_wizardlm_lora/resolve/main/added_tokens.json
21 Bytes
| { | |
| "[PAD]": 32000 | |
| } | |