stas's picture
copy from hf
d695a03
raw
history blame
698 Bytes
{
"architectures": [
"MistralForCausalLM"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 32,
"initializer_range": 0.02,
"intermediate_size": 37,
"is_decoder": true,
"max_position_embeddings": 512,
"model_type": "mistral",
"num_attention_heads": 4,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.34.0.dev0",
"type_vocab_size": 16,
"use_cache": true,
"vocab_size": 32000
}