Gryphe/Codex-24B-Small-3.2

1{2  "architectures": [3    "MistralForCausalLM"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 1,7  "eos_token_id": 999,8  "head_dim": 128,9  "hidden_act": "silu",10  "hidden_size": 5120,11  "initializer_range": 0.02,12  "intermediate_size": 32768,13  "max_position_embeddings": 131072,14  "model_type": "mistral",15  "num_attention_heads": 32,16  "num_hidden_layers": 40,17  "num_key_value_heads": 8,18  "rms_norm_eps": 1e-05,19  "rope_theta": 1000000000.0,20  "sliding_window": null,21  "tie_word_embeddings": false,22  "torch_dtype": "bfloat16",23  "transformers_version": "4.52.4",24  "use_cache": true,25  "vocab_size": 13107226}27