Llama-2-7b-NuGPTQ / config.json
smpanaro's picture
Initial commit
c2fa56c verified
raw
history blame contribute delete
739 Bytes
{
"architectures": [
"LLamaNuGPTQForCausalLM"
],
"auto_map": {
"AutoModelForCausalLM": "modeling_llama_nugptq.LLamaNuGPTQForCausalLM"
},
"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": 4096,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 32000
}