Instructions to use orvp/qaws with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use orvp/qaws with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8b") model = PeftModel.from_pretrained(base_model, "orvp/qaws") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-2/trainer_state.json from orvp/qaws: direct link, hf CLI and curl.
- Browser
- Download file 460 Bytes
-
https://huggingface.co/orvp/qaws/resolve/main/checkpoint-2/trainer_state.json
- Command line
-
hf download hf://orvp/qaws/checkpoint-2/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/orvp/qaws/resolve/main/checkpoint-2/trainer_state.json
460 Bytes
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8, | |
| "eval_steps": 500, | |
| "global_step": 2, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [], | |
| "logging_steps": 10, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 456258402385920.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |