TableLLM-13b-bpw2.5 / config.json
blockblockblock's picture
Upload folder using huggingface_hub
47b98c3 verified
{
"_name_or_path": "/data2/wangyuanchun/models/base_ckpt/llama2/CodeLlama-13b-Instruct-hf",
"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": 16384,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0",
"use_cache": true,
"vocab_size": 32016,
"quantization_config": {
"quant_method": "exl2",
"version": "0.0.16",
"bits": 2.5,
"head_bits": 6,
"calibration": {
"rows": 100,
"length": 2048,
"dataset": "(default)"
}
}
}