DaertML/phi-1-nf4-8bit-doublequant-BNB
017
1{2 "_name_or_path": "microsoft/phi-1",3 "activation_function": "gelu_new",4 "architecture": {5 "block_cls": "parallel",6 "mixer": {},7 "mlp": {8 "mlp_cls": "mlp"9 }10 },11 "architectures": [12 "MixFormerSequentialForCausalLM"13 ],14 "auto_map": {15 "AutoConfig": "microsoft/phi-1--configuration_mixformer_sequential.MixFormerSequentialConfig",16 "AutoModelForCausalLM": "microsoft/phi-1--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"17 },18 "embd_layer": "default",19 "embd_pdrop": 0.0,20 "initializer_range": 0.02,21 "layer_norm_epsilon": 1e-05,22 "model_type": "mixformer-sequential",23 "n_embd": 2048,24 "n_head": 32,25 "n_inner": null,26 "n_layer": 24,27 "n_positions": 2048,28 "phyagi_version": "0.0.4.dev",29 "quantization_config": {30 "bnb_4bit_compute_dtype": "bfloat16",31 "bnb_4bit_quant_type": "nf4",32 "bnb_4bit_use_double_quant": true,33 "llm_int8_enable_fp32_cpu_offload": false,34 "llm_int8_has_fp16_weight": false,35 "llm_int8_skip_modules": null,36 "llm_int8_threshold": 6.0,37 "load_in_4bit": false,38 "load_in_8bit": true,39 "quant_method": "bitsandbytes"40 },41 "resid_pdrop": 0.0,42 "rotary_dim": 32,43 "tie_word_embeddings": false,44 "torch_dtype": "float16",45 "transformers_version": "4.33.1",46 "vocab_size": 5120047}48 