Instructions to use hchang/reward_modeling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hchang/reward_modeling with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Meta-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "hchang/reward_modeling") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-3004/adapter_config.json from hchang/reward_modeling: direct link, hf CLI and curl.
- Browser
- Download file 642 Bytes
-
https://huggingface.co/hchang/reward_modeling/resolve/main/checkpoint-3004/adapter_config.json
- Command line
-
hf download hf://hchang/reward_modeling/checkpoint-3004/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/hchang/reward_modeling/resolve/main/checkpoint-3004/adapter_config.json
642 Bytes
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "gpt2", | |
| "bias": "none", | |
| "fan_in_fan_out": true, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.1, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": [ | |
| "classifier", | |
| "score" | |
| ], | |
| "peft_type": "LORA", | |
| "r": 8, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "c_attn" | |
| ], | |
| "task_type": "SEQ_CLS", | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |