Text Classification
PEFT
Safetensors
rag-gym
retrieval-augmented-generation
agent
lora
process-supervision
reward-model
Instructions to use RAG-Gym/ReSearch-HotpotQA-PRM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use RAG-Gym/ReSearch-HotpotQA-PRM with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "RAG-Gym/ReSearch-HotpotQA-PRM") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from RAG-Gym/ReSearch-HotpotQA-PRM: direct link, hf CLI and curl.
- Browser
- Download file 708 Bytes
-
https://huggingface.co/RAG-Gym/ReSearch-HotpotQA-PRM/resolve/main/adapter_config.json
- Command line
-
hf download hf://RAG-Gym/ReSearch-HotpotQA-PRM/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/RAG-Gym/ReSearch-HotpotQA-PRM/resolve/main/adapter_config.json
708 Bytes
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 512, | |
| "lora_dropout": 0.05, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": [ | |
| "classifier", | |
| "score" | |
| ], | |
| "peft_type": "LORA", | |
| "r": 256, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj" | |
| ], | |
| "task_type": "SEQ_CLS", | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |