MachineLearningLM/MachineLearningLM-7B-v1
3347
1{2 "architectures": [3 "Qwen2ForCausalLM"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "eos_token_id": 151645,8 "hidden_act": "silu",9 "hidden_size": 3584,10 "initializer_range": 0.02,11 "intermediate_size": 18944,12 "max_position_embeddings": 32768,13 "max_window_layers": 28,14 "model_type": "qwen2",15 "num_attention_heads": 28,16 "num_hidden_layers": 28,17 "num_key_value_heads": 4,18 "rms_norm_eps": 1e-06,19 "rope_scaling": {20 "factor": 4.0,21 "original_max_position_embeddings": 32768,22 "rope_type": "yarn",23 "type": "yarn"24 },25 "rope_theta": 1000000.0,26 "sliding_window": 131072,27 "tie_word_embeddings": false,28 "torch_dtype": "bfloat16",29 "transformers_version": "4.52.4",30 "use_cache": true,31 "use_sliding_window": false,32 "vocab_size": 15206433}34 