28 lines
643 B
JSON
28 lines
643 B
JSON
|
|
{
|
||
|
|
"architectures": [
|
||
|
|
"MistralForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 151849,
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 576,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 1536,
|
||
|
|
"max_position_embeddings": 8192,
|
||
|
|
"model_type": "mistral",
|
||
|
|
"num_attention_heads": 9,
|
||
|
|
"num_hidden_layers": 30,
|
||
|
|
"num_key_value_heads": 3,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_theta": 10000,
|
||
|
|
"sliding_window": 8192,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.44.2",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 151851
|
||
|
|
}
|