Starling-LM-10.7B-beta / config.json
ddh0's picture
Upload 11 files
ab55325 verified
raw
history blame
690 Bytes
{
"_name_or_path": "/media/dylan/Sabrent/LLMs/Starling-LM-7B-beta",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 48,
"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": "4.39.1",
"use_cache": true,
"vocab_size": 32002
}