42 lines
981 B
JSON
42 lines
981 B
JSON
{
|
|
"_name_or_path": "nicholasKluge/Aira-2-355M",
|
|
"activation_function": "gelu_new",
|
|
"architectures": [
|
|
"GPT2LMHeadModel"
|
|
],
|
|
"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": 1024,
|
|
"n_head": 16,
|
|
"n_inner": null,
|
|
"n_layer": 24,
|
|
"n_positions": 1024,
|
|
"n_special": 0,
|
|
"predict_special_tokens": true,
|
|
"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
|
|
}
|
|
},
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.33.1",
|
|
"use_cache": true,
|
|
"vocab_size": 50261
|
|
}
|