shareit/cycleinstruct-phi4-supervisor
011
1{2 "architectures": [3 "Phi3ForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 100257,8 "dtype": "bfloat16",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": 32768,16 "model_type": "phi3",17 "num_attention_heads": 40,18 "num_hidden_layers": 40,19 "num_key_value_heads": 10,20 "original_max_position_embeddings": 32768,21 "pad_token_id": 100349,22 "partial_rotary_factor": 1.0,23 "resid_pdrop": 0.0,24 "rms_norm_eps": 1e-05,25 "rope_parameters": {26 "partial_rotary_factor": 1.0,27 "rope_theta": 500000,28 "rope_type": "default"29 },30 "sliding_window": null,31 "tie_word_embeddings": false,32 "transformers_version": "5.12.1",33 "use_cache": true,34 "vocab_size": 10035235}36 