final-mle-again / config.json
kejian's picture
Training in progress, step 5000
1bd5562
raw
history blame
936 Bytes
{
"_name_or_path": "codeparrot/codeparrot-small",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMAndValueHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"reorder_and_upcast_attn": true,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": true,
"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
}
},
"torch_dtype": "float32",
"transformers_version": "4.23.0",
"use_cache": true,
"vocab_size": 32768
}