CoolFace
Modelpublic

boods/EnToFrMedicaLLM-Multilingual

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
0likes34downloads
config.json92 linesDownload Raw Back to root
1{2  "transformers_version": "5.5.0",3  "architectures": [4    "Qwen3ForCausalLM"5  ],6  "output_hidden_states": false,7  "return_dict": true,8  "dtype": "bfloat16",9  "chunk_size_feed_forward": 0,10  "is_encoder_decoder": false,11  "id2label": {12    "0": "LABEL_0",13    "1": "LABEL_1"14  },15  "label2id": {16    "LABEL_0": 0,17    "LABEL_1": 118  },19  "problem_type": null,20  "vocab_size": 151936,21  "hidden_size": 5120,22  "intermediate_size": 17408,23  "num_hidden_layers": 40,24  "num_attention_heads": 40,25  "num_key_value_heads": 8,26  "head_dim": 128,27  "hidden_act": "silu",28  "max_position_embeddings": 40960,29  "initializer_range": 0.02,30  "rms_norm_eps": 1e-06,31  "use_cache": true,32  "tie_word_embeddings": false,33  "rope_parameters": {34    "rope_theta": 1000000,35    "rope_type": "default"36  },37  "attention_bias": false,38  "use_sliding_window": false,39  "sliding_window": null,40  "max_window_layers": 40,41  "layer_types": [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    "full_attention",80    "full_attention",81    "full_attention"82  ],83  "attention_dropout": 0.0,84  "pad_token_id": 151669,85  "bos_token_id": null,86  "eos_token_id": 151645,87  "_name_or_path": "unsloth/Qwen3-14B-unsloth-bnb-4bit",88  "model_type": "qwen3",89  "unsloth_fixed": true,90  "unsloth_version": "2026.5.2",91  "output_attentions": false92}