R1pathak/phi-4-pruned50
03
1{2 "_name_or_path": "./phi_pruning/pruning_results_phi-4/models/model-pruned50-phi-4",3 "architectures": [4 "Phi3ForSequenceClassification"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 100257,9 "embd_pdrop": 0.0,10 "eos_token_id": 100265,11 "hidden_act": "silu",12 "hidden_size": 5120,13 "initializer_range": 0.02,14 "intermediate_size": 17920,15 "max_position_embeddings": 16384,16 "model_type": "phi3",17 "n_inner": 2560,18 "num_attention_heads": 40,19 "num_hidden_layers": 40,20 "num_key_value_heads": 10,21 "original_max_position_embeddings": 16384,22 "pad_token_id": 100349,23 "partial_rotary_factor": 1.0,24 "resid_pdrop": 0.0,25 "rms_norm_eps": 1e-05,26 "rope_scaling": null,27 "rope_theta": 250000,28 "sliding_window": null,29 "tie_word_embeddings": false,30 "torch_dtype": "float32",31 "transformers_version": "4.49.0",32 "use_cache": true,33 "vocab_size": 10035234}35 