dphn/Dolphin3.0-R1-Mistral-24B

1{2  "_name_or_path": "cognitivecomputations/Dolphin3.0-R1-Mistral-24B",3  "architectures": [4    "MistralForCausalLM"5  ],6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "eos_token_id": [2,131072],9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 5120,12  "initializer_range": 0.02,13  "intermediate_size": 32768,14  "max_position_embeddings": 32768,15  "model_type": "mistral",16  "num_attention_heads": 32,17  "num_hidden_layers": 40,18  "num_key_value_heads": 8,19  "rms_norm_eps": 1e-05,20  "rope_theta": 100000000.0,21  "sliding_window": null,22  "tie_word_embeddings": false,23  "torch_dtype": "bfloat16",24  "transformers_version": "4.48.1",25  "use_cache": false,26  "vocab_size": 13107427}28