llama-2-13b-awq-st / config.json
farrelramdhani's picture
Duplicate from genta-tech/llama-2-13b-awq
9d82472
raw
history blame
751 Bytes
{
"_name_or_path": "/root/.cache/huggingface/hub/models--meta-llama--Llama-2-13b-chat-hf/snapshots/c2f3ec81aac798ae26dcc57799a994dfbf521496",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.34.0",
"use_cache": true,
"vocab_size": 32000
}