TheBloke's picture
GPTQ model commit
a7759b1
{
"_name_or_path": "/workspace/process/deepseek-ai_deepseek-coder-6.7b-base/source",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 32013,
"eos_token_id": 32014,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"rope_theta": 100000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0",
"use_cache": true,
"vocab_size": 32256,
"quantization_config": {
"bits": 4,
"group_size": 128,
"damp_percent": 0.1,
"desc_act": true,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": "model",
"quant_method": "gptq"
}
}