27 lines
666 B
JSON
27 lines
666 B
JSON
{
|
|
"architectures": [
|
|
"MistralForCausalLM"
|
|
],
|
|
"attention_bias": true,
|
|
"attention_dropout": 0.0,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1024,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 2816,
|
|
"max_position_embeddings": 32768,
|
|
"max_window_layers": 21,
|
|
"model_type": "mistral",
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 16,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_theta": 1000000.0,
|
|
"rope_scaling": null,
|
|
"sliding_window": 32768,
|
|
"tie_word_embeddings": true,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.34.0.dev0",
|
|
"use_cache": true,
|
|
"use_sliding_window": true,
|
|
"vocab_size": 151936
|
|
} |