BigTranslate-13B-GPTQ / config.json
TheBloke's picture
Initial GPTQ model commit
0e16f43
raw
history blame
585 Bytes
{
"_name_or_path": "James-WYang/BigTrans",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"pad_token_id": -1,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.21.0",
"use_cache": true,
"vocab_size": 53613
}