NorGPT-369M / config.json
NorGLM's picture
Upload 5 files
631ecbc verified
raw
history blame contribute delete
865 Bytes
{
"_name_or_path": "/cluster/home/penl/workspace/checkpoints/gpt2/Megatron-huggingface/NorGLM-369M",
"activation_function": "gelu_fast",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 0,
"embd_pdrop": 0.1,
"eos_token_id": 0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 1024,
"n_head": 16,
"n_inner": 4096,
"n_layer": 24,
"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,
"tokenizer_class": "GPT2TokenizerFast",
"transformers_version": "4.30.0.dev0",
"use_cache": true,
"vocab_size": 64000
}