36 lines
821 B
JSON
36 lines
821 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 0,
|
||
|
|
"eos_token_id": 0,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 384,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 1408,
|
||
|
|
"max_position_embeddings": 131072,
|
||
|
|
"mlp_bias": false,
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 6,
|
||
|
|
"num_hidden_layers": 22,
|
||
|
|
"num_key_value_heads": 2,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": {
|
||
|
|
"factor": 8.0,
|
||
|
|
"high_freq_factor": 4.0,
|
||
|
|
"low_freq_factor": 1.0,
|
||
|
|
"original_max_position_embeddings": 8192,
|
||
|
|
"rope_type": "llama3"
|
||
|
|
},
|
||
|
|
"rope_theta": 10000,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.48.3",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 49152
|
||
|
|
}
|