CoolFace
Modelpublic

seanpoyner/smolcode-coder-java-3b-tools

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes93downloads
config.json70 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": 2048,11  "initializer_range": 0.02,12  "intermediate_size": 11008,13  "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    "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  ],51  "max_position_embeddings": 32768,52  "max_window_layers": 36,53  "model_type": "qwen2",54  "num_attention_heads": 16,55  "num_hidden_layers": 36,56  "num_key_value_heads": 2,57  "pad_token_id": null,58  "rms_norm_eps": 1e-06,59  "rope_parameters": {60    "rope_theta": 1000000.0,61    "rope_type": "default"62  },63  "sliding_window": null,64  "tie_word_embeddings": false,65  "transformers_version": "5.12.0",66  "use_cache": true,67  "use_sliding_window": false,68  "vocab_size": 15193669}70