ChenMnZ's picture
Upload folder using huggingface_hub
469042a verified
raw
history blame
1.33 kB
{
"_name_or_path": "/cpfs01/user/chenmengzhao/efficientqat_repo/efficientqat_checkpoints_original/Llama-2-13b-EfficientQAT-w4g128",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"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,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"checkpoint_format": "bitblas",
"damp_percent": 0.01,
"desc_act": false,
"group_size": 128,
"lm_head": false,
"meta": {
"quantizer": "gptqmodel:0.9.9-dev0"
},
"model_file_base_name": null,
"model_name_or_path": "/cpfs01/user/chenmengzhao/efficientqat_repo/efficientqat_checkpoints_original/Llama-2-13b-EfficientQAT-w4g128",
"quant_method": "gptq",
"static_groups": false,
"sym": false,
"true_sequential": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.42.4",
"use_cache": false,
"vocab_size": 32001
}