normistral-7b-warm / config.json
davda54's picture
Upload folder using huggingface_hub
ddd8bda verified
raw
history blame
591 Bytes
{
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 2048,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 2048,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0.dev0",
"use_cache": true,
"vocab_size": 32768
}