distilGPT-NepSA / config.json
raygx's picture
Upload TFGPT2ForSequenceClassification
ba46a60
raw
history blame
1.1 kB
{
"_name_or_path": "raygx/Nepali-DistilGPT2",
"_num_labels": 1,
"activation_function": "gelu_new",
"architectures": [
"GPT2ForSequenceClassification"
],
"attn_pdrop": 0.1,
"bos_token_id": 1,
"embd_pdrop": 0.1,
"eos_token_id": 2,
"id2label": {
"0": "NEUTRAL",
"1": "POSITIVE",
"2": "NEGATIVE"
},
"initializer_range": 0.02,
"label2id": {
"NEGATIVE": 2,
"NEUTRAL": 0,
"POSITIVE": 1
},
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 6,
"n_inner": null,
"n_layer": 6,
"n_positions": 1024,
"pad_token_id": 3,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"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
}
},
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 50000
}