tensoropera/Fox-1-1.6B

1{2  "architectures": [3    "LlamaForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 1,8  "eos_token_id": 2,9  "hidden_act": "silu",10  "hidden_size": 2048,11  "initializer_range": 0.02,12  "intermediate_size": 4096,13  "max_position_embeddings": 8192,14  "model_type": "llama",15  "num_attention_heads": 16,16  "num_hidden_layers": 32,17  "num_key_value_heads": 4,18  "pretraining_tp": 1,19  "rms_norm_eps": 1e-05,20  "rope_scaling": null,21  "rope_theta": 10000.0,22  "tie_word_embeddings": true,23  "torch_dtype": "bfloat16",24  "transformers_version": "4.39.3",25  "use_cache": true,26  "vocab_size": 25600027}28