tinyllama-1b-awq-gemv / config.json
casperhansen's picture
Update config.json
b3460e4
{
"_name_or_path": "/root/.cache/huggingface/hub/models--PY007--TinyLlama-1.1B-intermediate-step-240k-503b/snapshots/a016b960b941eb6eb7884e363b935370bafa5932",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"quant_method": "awq",
"version": "gemv",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.33.2",
"use_cache": true,
"vocab_size": 32000
}