nithin093/phi3-jee-model
013
1{2 "architectures": [3 "MistralForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 1,7 "torch_dtype": "float16",8 "eos_token_id": 32000,9 "head_dim": 96,10 "hidden_act": "silu",11 "hidden_size": 3072,12 "initializer_range": 0.02,13 "intermediate_size": 8192,14 "max_position_embeddings": 4096,15 "model_type": "mistral",16 "num_attention_heads": 32,17 "num_hidden_layers": 32,18 "num_key_value_heads": 32,19 "pad_token_id": 32009,20 "rms_norm_eps": 1e-05,21 "rope_parameters": {22 "rope_theta": 10000.0,23 "rope_type": "default"24 },25 "sliding_window": 2048,26 "tie_word_embeddings": false,27 "unsloth_version": "2026.5.2",28 "use_cache": false,29 "vocab_size": 3206430}