b7dcd0bfe4
Model: abehandlerorg/dobolyilab-blockbench-blocksbin_rlhf_dpo_hh-rlhf_e1_lr5e-5_r8 Source: Original Platform
36 lines
852 B
JSON
36 lines
852 B
JSON
{
|
|
"activation_function": "gelu_new",
|
|
"add_cross_attention": false,
|
|
"architectures": [
|
|
"GPT2LMHeadModel"
|
|
],
|
|
"attn_pdrop": 0.1,
|
|
"bos_token_id": 50256,
|
|
"dtype": "bfloat16",
|
|
"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": 1600,
|
|
"n_head": 25,
|
|
"n_inner": null,
|
|
"n_layer": 48,
|
|
"n_positions": 1024,
|
|
"pad_token_id": 50256,
|
|
"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,
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "5.2.0",
|
|
"use_cache": false,
|
|
"vocab_size": 50257
|
|
}
|