|
{ |
|
"_name_or_path": "meta-llama/Llama-3.2-3B-Instruct", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 128000, |
|
"eos_token_id": [ |
|
128001, |
|
128008, |
|
128009 |
|
], |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 3072, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8192, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 2048, |
|
"model_type": "llama", |
|
"num_attention_heads": 24, |
|
"num_hidden_layers": 24, |
|
"pad_token_id": 0, |
|
"rms_norm_eps": 1e-06, |
|
"vocab_size": 32000 |
|
} |