distilgpt2 / config.json
bmah-dmx's picture
Added DistilGPT2 model
710ed6f
raw
history blame contribute delete
974 Bytes
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"auto_map": {
"AutoConfig": "configuration_gpt2.GPT2Config",
"AutoModelForCausalLM": "modeling_gpt2.GPT2LMHeadModel"
},
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"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,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_layer": 6,
"n_positions": 1024,
"resid_pdrop": 0.1,
"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
}
},
"vocab_size": 50257
}