mistral-7b-sft / config.json
abacaj's picture
Upload MistralForCausalLM
00ad477
{
"_name_or_path": "/home/anton/personal/transformer-experiments/outputs/mistralai/Mistral-7B-v0.1/ba34c6ea-67e8-48fd-abb6-03d527234e2a",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 32000,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0.dev0",
"use_cache": false,
"vocab_size": 32001
}