Instructions to use atharvgaur18/actionproof-rft-tiny-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use atharvgaur18/actionproof-rft-tiny-v2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global") model = PeftModel.from_pretrained(base_model, "atharvgaur18/actionproof-rft-tiny-v2") - Notebooks
- Google Colab
- Kaggle
Download run_config.json from atharvgaur18/actionproof-rft-tiny-v2: direct link, hf CLI and curl.
- Browser
- Download file 248 Bytes
-
https://huggingface.co/atharvgaur18/actionproof-rft-tiny-v2/resolve/main/run_config.json
- Command line
-
hf download hf://atharvgaur18/actionproof-rft-tiny-v2/run_config.json
-
curl -L -o run_config.json https://huggingface.co/atharvgaur18/actionproof-rft-tiny-v2/resolve/main/run_config.json
248 Bytes
| { | |
| "data": "data/rft/curated_v2_32b.jsonl", | |
| "model": "CohereLabs/tiny-aya-global", | |
| "out": "runs/rft_tiny_v2", | |
| "epochs": 2.0, | |
| "lr": 0.0001, | |
| "batch": 2, | |
| "grad_accum": 8, | |
| "max_length": 6144, | |
| "lora_r": 16, | |
| "seed": 0, | |
| "rows": 2265 | |
| } |