gpt-j-reward-model / config.json
zpn's picture
Upload model
779c83e
raw
history blame
1.27 kB
{
"_name_or_path": "/mnt/nvme/home/zanussbaum/.cache/huggingface/hub/models--LawInformedAI--reward_model_epoch_0/snapshots/2f4cc4d6ce97d6cfdb43d225e47f1736a72e5152/",
"activation_function": "gelu_new",
"architectures": [
"RewardModel"
],
"attn_pdrop": 0.0,
"auto_map": {
"AutoConfig": "configuration_reward_model.RewardConfig",
"AutoModel": "modeling_rewards.RewardModel"
},
"base_model": "LawInformedAI/gptj-finetuned_court_opinions",
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"n_embd": 4096,
"n_head": 16,
"n_inner": null,
"n_layer": 28,
"n_positions": 2048,
"pad_id": null,
"resid_pdrop": 0.0,
"rotary": true,
"rotary_dim": 64,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50,
"temperature": 1.0
}
},
"tie_word_embeddings": false,
"tokenizer_class": "GPT2Tokenizer",
"torch_dtype": "float32",
"transformers_version": "4.27.4",
"use_cache": false,
"vocab_size": 50400
}