CoolFace
Modelpublic

OpenHands/CodeScout-14B

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
4likes119downloads
config.json74 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3ForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 151643,8  "dtype": "bfloat16",9  "eos_token_id": 151645,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 5120,13  "initializer_range": 0.02,14  "intermediate_size": 17408,15  "layer_types": [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  ],57  "max_position_embeddings": 40960,58  "max_window_layers": 40,59  "model_type": "qwen3",60  "num_attention_heads": 40,61  "num_hidden_layers": 40,62  "num_key_value_heads": 8,63  "pad_token_id": 151643,64  "rms_norm_eps": 1e-06,65  "rope_scaling": null,66  "rope_theta": 1000000,67  "sliding_window": null,68  "tie_word_embeddings": false,69  "transformers_version": "4.57.3",70  "use_cache": false,71  "use_sliding_window": false,72  "vocab_size": 15193673}74