CoolFace
Modelpublic

nivethitha1703/developer-git-commit-agent

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face
1likes560downloads
config.json58 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen2ForCausalLM"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151643,7  "dtype": "bfloat16",8  "eos_token_id": 151645,9  "hidden_act": "silu",10  "hidden_size": 896,11  "initializer_range": 0.02,12  "intermediate_size": 4864,13  "layer_types": [14    "full_attention",15    "full_attention",16    "full_attention",17    "full_attention",18    "full_attention",19    "full_attention",20    "full_attention",21    "full_attention",22    "full_attention",23    "full_attention",24    "full_attention",25    "full_attention",26    "full_attention",27    "full_attention",28    "full_attention",29    "full_attention",30    "full_attention",31    "full_attention",32    "full_attention",33    "full_attention",34    "full_attention",35    "full_attention",36    "full_attention",37    "full_attention"38  ],39  "max_position_embeddings": 32768,40  "max_window_layers": 24,41  "model_type": "qwen2",42  "num_attention_heads": 14,43  "num_hidden_layers": 24,44  "num_key_value_heads": 2,45  "pad_token_id": null,46  "rms_norm_eps": 1e-06,47  "rope_parameters": {48    "rope_theta": 1000000.0,49    "rope_type": "default"50  },51  "sliding_window": null,52  "tie_word_embeddings": true,53  "transformers_version": "5.15.1",54  "use_cache": true,55  "use_sliding_window": false,56  "vocab_size": 15193657}58