Instructions to use sumith2425/ppo-prefix-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use sumith2425/ppo-prefix-model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2-medium") model = PeftModel.from_pretrained(base_model, "sumith2425/ppo-prefix-model") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from sumith2425/ppo-prefix-model: direct link, hf CLI and curl.
- Browser
- Download file 442 Bytes
-
https://huggingface.co/sumith2425/ppo-prefix-model/resolve/main/adapter_config.json
- Command line
-
hf download hf://sumith2425/ppo-prefix-model/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/sumith2425/ppo-prefix-model/resolve/main/adapter_config.json
442 Bytes
| { | |
| "auto_mapping": null, | |
| "base_model_name_or_path": "openai-community/gpt2-medium", | |
| "encoder_hidden_size": 1024, | |
| "inference_mode": true, | |
| "modules_to_save": null, | |
| "num_attention_heads": 16, | |
| "num_layers": 24, | |
| "num_transformer_submodules": 1, | |
| "num_virtual_tokens": 30, | |
| "peft_type": "PREFIX_TUNING", | |
| "peft_version": "0.18.1", | |
| "prefix_projection": false, | |
| "revision": null, | |
| "task_type": "CAUSAL_LM", | |
| "token_dim": 1024 | |
| } |