capleaf-T-Llama / config.json
hflog's picture
Duplicate from capleaf/T-Llama
794e279 verified
raw
history blame contribute delete
743 Bytes
{
"_name_or_path": "1TuanPham/InstructEnVi_llama2-bkai-120GB-Orcafamily_250kx3.37",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.1",
"use_cache": true,
"vocab_size": 45452
}