59 lines
1.4 KiB
JSON
59 lines
1.4 KiB
JSON
|
{
|
||
|
|
"_name_or_path": "microsoft/phi-4",
|
||
|
|
"architectures": [
|
||
|
|
"Phi3ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"auto_map": {},
|
||
|
|
"bos_token_id": 100257,
|
||
|
|
"embd_pdrop": 0.0,
|
||
|
|
"eos_token_id": 100257,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 5120,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 17920,
|
||
|
|
"max_position_embeddings": 16384,
|
||
|
|
"model_type": "phi3",
|
||
|
|
"num_attention_heads": 40,
|
||
|
|
"num_hidden_layers": 40,
|
||
|
|
"num_key_value_heads": 10,
|
||
|
|
"original_max_position_embeddings": 16384,
|
||
|
|
"pad_token_id": 100257,
|
||
|
|
"quantization_config": {
|
||
|
|
"amp": true,
|
||
|
|
"autoround_version": "0.4.4",
|
||
|
|
"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": 256,
|
||
|
|
"low_gpu_mem_usage": false,
|
||
|
|
"lr": 0.00390625,
|
||
|
|
"minmax_lr": 0.00390625,
|
||
|
|
"nsamples": 128,
|
||
|
|
"quant_method": "gptq",
|
||
|
|
"scale_dtype": "torch.float16",
|
||
|
|
"seqlen": 2048,
|
||
|
|
"sym": true,
|
||
|
|
"to_quant_block_names": null,
|
||
|
|
"true_sequential": false
|
||
|
|
},
|
||
|
|
"resid_pdrop": 0.0,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 250000,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.47.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 100352
|
||
|
|
}
|