CoolFace
Modelpublic

CodeAid/Refactoring_solid_model

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes14downloads
config.json79 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": 151645,8  "hidden_act": "silu",9  "hidden_size": 5120,10  "initializer_range": 0.02,11  "intermediate_size": 13824,12  "layer_types": [13    "full_attention",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    "full_attention",39    "full_attention",40    "full_attention",41    "full_attention",42    "full_attention",43    "full_attention",44    "full_attention",45    "full_attention",46    "full_attention",47    "full_attention",48    "full_attention",49    "full_attention",50    "full_attention",51    "full_attention",52    "full_attention",53    "full_attention",54    "full_attention",55    "full_attention",56    "full_attention",57    "full_attention",58    "full_attention",59    "full_attention",60    "full_attention"61  ],62  "max_position_embeddings": 32768,63  "max_window_layers": 70,64  "model_type": "qwen2",65  "num_attention_heads": 40,66  "num_hidden_layers": 48,67  "num_key_value_heads": 8,68  "rms_norm_eps": 1e-06,69  "rope_scaling": null,70  "rope_theta": 1000000.0,71  "sliding_window": null,72  "tie_word_embeddings": false,73  "torch_dtype": "float16",74  "transformers_version": "4.53.0",75  "use_cache": true,76  "use_sliding_window": false,77  "vocab_size": 15206478}79