phxdev's picture
Create config.json
61d343a verified
raw
history blame contribute delete
610 Bytes
{
"architectures": ["MistralForCausalLM"],
"model_type": "mistral",
"vocab_size": 32000,
"hidden_size": 4096,
"intermediate_size": 14336,
"num_hidden_layers": 32,
"num_attention_heads": 32,
"num_key_value_heads": 8,
"hidden_act": "silu",
"max_position_embeddings": 32768,
"initializer_range": 0.02,
"rms_norm_eps": 1e-05,
"use_cache": true,
"pad_token_id": null,
"bos_token_id": 1,
"eos_token_id": 2,
"tie_word_embeddings": false,
"rope_theta": 1000000.0,
"sliding_window": null,
"attention_dropout": 0.0,
"torch_dtype": "float16",
"transformers_version": "4.38.0"
}