57 lines
1.3 KiB
JSON
57 lines
1.3 KiB
JSON
{
|
|
"_name_or_path": "/models/Meta-Llama-3.1-8B-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": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"max_position_embeddings": 131072,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"pretraining_tp": 1,
|
|
"quantization_config": {
|
|
"amp": true,
|
|
"autoround_version": "0.5.1",
|
|
"batch_size": 8,
|
|
"bits": 4,
|
|
"data_type": "int",
|
|
"dataset": "NeelNanda/pile-10k",
|
|
"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": false,
|
|
"lr": 0.001,
|
|
"minmax_lr": 0.001,
|
|
"nsamples": 512,
|
|
"quant_method": "auto-round",
|
|
"scale_dtype": "torch.float16",
|
|
"seqlen": 2048,
|
|
"sym": true
|
|
},
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 500000.0,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.52.2",
|
|
"use_cache": true,
|
|
"vocab_size": 128256
|
|
}
|