|
{ |
|
"activation_function": "gelu_new", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"attn_pdrop": 0.1, |
|
"bos_token_id": 128000, |
|
"embd_pdrop": 0.1, |
|
"eos_token_id": 128001, |
|
"hidden_act": "silu", |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "gpt2", |
|
"n_embd": 4096, |
|
"n_head": 32, |
|
"n_inner": null, |
|
"n_layer": 32, |
|
"n_positions": 8192, |
|
"num_key_value_heads": 8, |
|
"pretraining_tp": 1, |
|
"reorder_and_upcast_attn": false, |
|
"resid_pdrop": 0.1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 500000.0, |
|
"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, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.41.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 128256 |
|
} |
|
|