|
{ |
|
"_name_or_path": "llm-jp/llm-jp-3-3.7b-instruct", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 3072, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8192, |
|
"max_position_embeddings": 32768, |
|
"mlp_bias": false, |
|
"model_type": "llama", |
|
"num_attention_heads": 24, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 24, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.46.1", |
|
"use_cache": false, |
|
"vocab_size": 99584 |
|
} |
|
|