llm-jp-13b-v1.0 / config.json
losyer8's picture
Upload model
b0d611d
raw
history blame
997 Bytes
{
"_name_or_path": "/data/llmjp0/model_cache_dir/outputs/checkpoint_HF/13B/ds_gpt_v101_fattn_nfs_0825_refined-data-gpt_13B_refined_gpu96_node12_lr0.00008533_gbs1536_mbs1_nwk2_zero1_pp8/global_step96657",
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 7,
"embd_pdrop": 0.1,
"eos_token_id": 7,
"gradient_checkpointing": false,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 5120,
"n_head": 40,
"n_inner": 20480,
"n_layer": 40,
"n_positions": 2048,
"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,
"torch_dtype": "float16",
"transformers_version": "4.34.0",
"use_cache": true,
"vocab_size": 50688
}