37 lines
1.1 KiB
JSON
37 lines
1.1 KiB
JSON
{
|
|
"model_name": "bling-cerebras-1.3b-0.1",
|
|
"description": "Instruct train fine-tuning using distilled knowledge based critical reading tasks training dataset",
|
|
"training_timestamp": "Sat Oct 7 08:52:05 2023",
|
|
"training_comments": "cerebras-1.3b-base",
|
|
"_name_or_path": "cerebras/Cerebras-GPT-1.3B",
|
|
"architectures": [
|
|
"GPT2LMHeadModel"
|
|
],
|
|
"activation_function": "gelu",
|
|
"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": 2048,
|
|
"n_head": 16,
|
|
"n_inner": 8192,
|
|
"n_layer": 24,
|
|
"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,
|
|
"transformers_version": "4.33.2",
|
|
"use_cache": true,
|
|
"vocab_size": 50257
|
|
}
|
|
|