CoolFace
Modelpublic

RedMod/speedrun_model

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes4downloads
config.json65 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  "eos_token_id": 151643,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 2048,12  "initializer_range": 0.02,13  "intermediate_size": 6144,14  "layer_types": [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  ],48  "max_position_embeddings": 32768,49  "max_window_layers": 32,50  "model_type": "qwen3",51  "num_attention_heads": 16,52  "num_hidden_layers": 32,53  "num_key_value_heads": 8,54  "rms_norm_eps": 1e-06,55  "rope_scaling": null,56  "rope_theta": 1000000,57  "sliding_window": null,58  "tie_word_embeddings": true,59  "torch_dtype": "bfloat16",60  "transformers_version": "4.55.2",61  "use_cache": false,62  "use_sliding_window": false,63  "vocab_size": 15193664}65