CoolFace
Modelpublic

praful1/Qwen-0.6b-pythoncode-instruct

sourceHugging Faceupdated 27d agoView on Hugging Face
0likes667downloads
config.json64 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3ForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": null,8  "dtype": "bfloat16",9  "eos_token_id": 151643,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 1024,13  "initializer_range": 0.02,14  "intermediate_size": 3072,15  "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  ],45  "max_position_embeddings": 32768,46  "max_window_layers": 28,47  "model_type": "qwen3",48  "num_attention_heads": 16,49  "num_hidden_layers": 28,50  "num_key_value_heads": 8,51  "pad_token_id": 151643,52  "rms_norm_eps": 1e-06,53  "rope_parameters": {54    "rope_theta": 1000000,55    "rope_type": "default"56  },57  "sliding_window": null,58  "tie_word_embeddings": true,59  "transformers_version": "5.15.0",60  "use_cache": false,61  "use_sliding_window": false,62  "vocab_size": 15193663}64