Instructions to use jbb/llama_coq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jbb/llama_coq with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf") model = PeftModel.from_pretrained(base_model, "jbb/llama_coq") - Notebooks
- Google Colab
- Kaggle
metadata
library_name: peft
base_model: codellama/CodeLlama-7b-hf
license: mit
datasets:
- jbb/coq_code
Model Card for Model ID
Model Details
Model Description
- Developed by: me
- License: mit
- Finetuned from model: codellama/CodeLlama-7b-hf
Uses
For generating code for mathematical formalization.
Training Details
Training Data
codellama/CodeLlama-7b-hf jbb/coq_code
Training Procedure
peft
Metrics
https://wandb.ai/jaeson/coq-coder/reports/peft-llama-coq--Vmlldzo2MzY1NzYy
Results
https://wandb.ai/jaeson/coq-coder/runs/slare690?workspace=user-jaeson
- PEFT 0.7.2.dev0
