gpt2-imdb-sequence-rm / config.json
chadlzx
Initial commit
d94a156
raw
history blame contribute delete
No virus
1.23 kB
{
"_name_or_path": "/mnt/petrelfs/share_data/llm-safety/models/gpt2",
"activation_function": "gelu_new",
"architectures": [
"GPT2ForScore"
],
"attn_pdrop": 0.1,
"bias": false,
"bos_token_id": 50256,
"do_normalize": false,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"id2label": {
"0": "LABEL_0"
},
"initializer_range": 0.02,
"label2id": {
"LABEL_0": 0
},
"layer_norm_epsilon": 1e-05,
"mean": [
-0.3359375
],
"model_type": "gpt2",
"momentum": 0.9,
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"normalizer_type": "ExponentialMovingAverage",
"pad_token_id": 50256,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"score_dim": 1,
"score_type": "reward",
"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
}
},
"transformers_version": "4.34.0",
"use_cache": true,
"var": [
2.625
],
"vocab_size": 50257
}