Starling-LM-7B-alpha / config.json
banghua's picture
Duplicate from banghua/openchat-3.5-ppo-ckpt-6k
fa6178c
raw
history blame
613 Bytes
{
"_name_or_path": "openchat/openchat_3.5",
"architectures": [
"MistralForCausalLM"
],
"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": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 32002
}