Instructions to use wesley7137/MetaMath-CodeLlama-Python-7B-V1-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use wesley7137/MetaMath-CodeLlama-Python-7B-V1-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-Python-hf") model = PeftModel.from_pretrained(base_model, "wesley7137/MetaMath-CodeLlama-Python-7B-V1-lora") - Notebooks
- Google Colab
- Kaggle
Download added_tokens.json from wesley7137/MetaMath-CodeLlama-Python-7B-V1-lora: direct link, hf CLI and curl.
- Browser
- Download file 87 Bytes
-
https://huggingface.co/wesley7137/MetaMath-CodeLlama-Python-7B-V1-lora/resolve/main/added_tokens.json
- Command line
-
hf download hf://wesley7137/MetaMath-CodeLlama-Python-7B-V1-lora/added_tokens.json
-
curl -L -o added_tokens.json https://huggingface.co/wesley7137/MetaMath-CodeLlama-Python-7B-V1-lora/resolve/main/added_tokens.json
87 Bytes
| { | |
| "▁<EOT>": 32003, | |
| "▁<MID>": 32001, | |
| "▁<PRE>": 32000, | |
| "▁<SUF>": 32002 | |
| } | |