Unbabel/Tower-Plus-72B
22162
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "hidden_act": "silu",7 "hidden_size": 8192,8 "initializer_range": 0.02,9 "intermediate_size": 29568,10 "max_position_embeddings": 32768,11 "max_window_layers": 28,12 "model_type": "qwen2",13 "num_attention_heads": 64,14 "num_hidden_layers": 80,15 "num_key_value_heads": 8,16 "rms_norm_eps": 1e-06,17 "rope_scaling": null,18 "rope_theta": 10000.0,19 "sliding_window": null,20 "tie_word_embeddings": false,21 "torch_dtype": "bfloat16",22 "transformers_version": "4.51.1",23 "use_cache": false,24 "use_sliding_window": false,25 "vocab_size": 15206426}27 