CoolFace
Modelpublic

AscendKernelGen/KernelGen-LM-32B-RL

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
1likes36downloads
config.json97 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": 151645,9  "head_dim": 128,10  "hidden_act": "silu",11  "hidden_size": 5120,12  "initializer_range": 0.02,13  "intermediate_size": 25600,14  "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    "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    "full_attention",62    "full_attention",63    "full_attention",64    "full_attention",65    "full_attention",66    "full_attention",67    "full_attention",68    "full_attention",69    "full_attention",70    "full_attention",71    "full_attention",72    "full_attention",73    "full_attention",74    "full_attention",75    "full_attention",76    "full_attention",77    "full_attention",78    "full_attention"79  ],80  "max_position_embeddings": 40960,81  "max_window_layers": 64,82  "model_type": "qwen3",83  "num_attention_heads": 64,84  "num_hidden_layers": 64,85  "num_key_value_heads": 8,86  "rms_norm_eps": 1e-06,87  "rope_scaling": null,88  "rope_theta": 1000000,89  "sliding_window": null,90  "tie_word_embeddings": false,91  "torch_dtype": "bfloat16",92  "transformers_version": "4.53.0",93  "use_cache": true,94  "use_sliding_window": false,95  "vocab_size": 15193696}97