LaMini-Cerebras-256M / config.json
macabdul9's picture
Upload model (#1)
f944785
raw
history blame
838 Bytes
{
"_name_or_path": "/home/awaheed/scratch/InstructTuning/output/Cerebras-GPT-256M",
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.0,
"bos_token_id": 50256,
"embd_pdrop": 0.0,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 1088,
"n_head": 17,
"n_inner": 4352,
"n_layer": 14,
"n_positions": 2048,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.0,
"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,
"torch_dtype": "float32",
"transformers_version": "4.28.0.dev0",
"use_cache": false,
"vocab_size": 50258
}