Instructions to use Prathyusha101/reset_value_head with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Prathyusha101/reset_value_head with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Prathyusha101/reset_value_head", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download value_model/config.json from Prathyusha101/reset_value_head: direct link, hf CLI and curl.
- Browser
- Download file 849 Bytes
-
https://huggingface.co/Prathyusha101/reset_value_head/resolve/main/value_model/config.json
- Command line
-
hf download hf://Prathyusha101/reset_value_head/value_model/config.json
-
curl -L -o config.json https://huggingface.co/Prathyusha101/reset_value_head/resolve/main/value_model/config.json
849 Bytes
| { | |
| "architectures": [ | |
| "GPTNeoXForSequenceClassification" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "classifier_dropout": 0.1, | |
| "eos_token_id": 0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "gpt_neox", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 16, | |
| "partial_rotary_factor": 0.25, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "rotary_emb_base": 10000, | |
| "rotary_pct": 0.25, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.53.1", | |
| "use_cache": true, | |
| "use_parallel_residual": true, | |
| "vocab_size": 50304 | |
| } | |