|
{ |
|
"_name_or_path": "/data5/Llama-3.3-70B-Instruct", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 128000, |
|
"eos_token_id": [ |
|
128001, |
|
128008, |
|
128009 |
|
], |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 8192, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 28672, |
|
"max_position_embeddings": 131072, |
|
"mlp_bias": false, |
|
"model_type": "llama", |
|
"num_attention_heads": 64, |
|
"num_hidden_layers": 80, |
|
"num_key_value_heads": 8, |
|
"pretraining_tp": 1, |
|
"quantization_config": { |
|
"amp": true, |
|
"autoround_version": "0.4.2.dev", |
|
"batch_size": 8, |
|
"bits": 4, |
|
"damp_percent": 0.01, |
|
"data_type": "int", |
|
"desc_act": false, |
|
"enable_minmax_tuning": true, |
|
"enable_norm_bias_tuning": false, |
|
"enable_quanted_input": true, |
|
"gradient_accumulate_steps": 1, |
|
"group_size": 128, |
|
"iters": 1000, |
|
"low_gpu_mem_usage": true, |
|
"lr": 0.001, |
|
"minmax_lr": 0.001, |
|
"nsamples": 512, |
|
"quant_method": "gptq", |
|
"scale_dtype": "torch.float16", |
|
"seqlen": 2048, |
|
"sym": true, |
|
"to_quant_block_names": null, |
|
"true_sequential": false |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": { |
|
"factor": 8.0, |
|
"high_freq_factor": 4.0, |
|
"low_freq_factor": 1.0, |
|
"original_max_position_embeddings": 8192, |
|
"rope_type": "llama3" |
|
}, |
|
"rope_theta": 500000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.47.0", |
|
"use_cache": true, |
|
"vocab_size": 128256 |
|
} |
|
|