|
{ |
|
"_name_or_path": "/home/heyjoonkim/data/uncertainty/orca/NEW/epoch-3_batch-8_accumulation-4_lr-2e-05/meta-llama_Llama-2-7b-hf/full", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_position_embeddings": 4096, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.32.0.dev0", |
|
"use_cache": false, |
|
"vocab_size": 32001 |
|
} |
|
|