phi3-gptq-8bits / config.json
ludekcizinsky's picture
Upload Phi3ForCausalLM
f601307 verified
raw
history blame
1.61 kB
{
"_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
"architectures": [
"Phi3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
"AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
},
"bos_token_id": 1,
"embd_pdrop": 0.0,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 4096,
"model_type": "phi3",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"original_max_position_embeddings": 4096,
"pad_token_id": 32000,
"quantization_config": {
"batch_size": 1,
"bits": 8,
"block_name_to_quantize": null,
"cache_block_outputs": true,
"damp_percent": 0.1,
"dataset": "c4",
"desc_act": false,
"exllama_config": {
"version": 1
},
"group_size": 128,
"max_input_length": null,
"model_seqlen": null,
"module_name_preceding_first_block": null,
"modules_in_block_to_quantize": null,
"pad_token_id": null,
"quant_method": "gptq",
"sym": true,
"tokenizer": null,
"true_sequential": true,
"use_cuda_fp16": false,
"use_exllama": true
},
"resid_pdrop": 0.0,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"sliding_window": 2047,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.41.2",
"use_cache": true,
"vocab_size": 32064
}