Team Ai
Modelpublic

realYinkaIyiola/Deepseek-R1-Distill-14B-Math-Code-Merged

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes30downloads
config.json29 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen2ForCausalLM"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151643,7  "eos_token_id": 151643,8  "hidden_act": "silu",9  "hidden_size": 5120,10  "initializer_range": 0.02,11  "intermediate_size": 13824,12  "max_position_embeddings": 131072,13  "max_window_layers": 48,14  "model_type": "qwen2",15  "num_attention_heads": 40,16  "num_hidden_layers": 48,17  "num_key_value_heads": 8,18  "rms_norm_eps": 1e-05,19  "rope_scaling": null,20  "rope_theta": 1000000.0,21  "sliding_window": 131072,22  "tie_word_embeddings": false,23  "torch_dtype": "bfloat16",24  "transformers_version": "4.50.0",25  "use_cache": true,26  "use_sliding_window": false,27  "vocab_size": 15206428}29