CoolFace
Modelpublic

RedHatAI/phi-2-super-marlin

sourceHugging Facemitupdated 3y agoView on Hugging Face
1likes29downloads
config.json48 linesDownload Raw Back to root
1{2  "_name_or_path": "phi-2-super-gptq",3  "architectures": [4    "PhiForCausalLM"5  ],6  "attention_dropout": 0.0,7  "auto_map": {8    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",9    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"10  },11  "bos_token_id": 50256,12  "embd_pdrop": 0.0,13  "eos_token_id": 50256,14  "hidden_act": "gelu_new",15  "hidden_size": 2560,16  "initializer_range": 0.02,17  "intermediate_size": 10240,18  "layer_norm_eps": 1e-05,19  "max_position_embeddings": 2048,20  "model_type": "phi",21  "num_attention_heads": 32,22  "num_hidden_layers": 32,23  "num_key_value_heads": 32,24  "partial_rotary_factor": 0.4,25  "qk_layernorm": false,26  "quantization_config": {27    "bits": 4,28    "damp_percent": 0.01,29    "desc_act": false,30    "group_size": 128,31    "is_marlin_format": true,32    "model_file_base_name": "model",33    "model_name_or_path": "phi-2-super-gptq",34    "quant_method": "gptq",35    "static_groups": false,36    "sym": true,37    "true_sequential": true38  },39  "resid_pdrop": 0.1,40  "rope_scaling": null,41  "rope_theta": 10000.0,42  "tie_word_embeddings": false,43  "torch_dtype": "float16",44  "transformers_version": "4.38.2",45  "use_cache": true,46  "vocab_size": 5120047}48