BERRAMOU/qwen-math-classification
022
1{2 "architectures": [3 "Qwen2ForSequenceClassification"4 ],5 "attention_dropout": 0.0,6 "bos_token_id": 151643,7 "dtype": "float32",8 "eos_token_id": 151643,9 "hidden_act": "silu",10 "hidden_size": 896,11 "id2label": {12 "0": "Correct",13 "1": "Partiellement correct",14 "2": "Incorrect"15 },16 "initializer_range": 0.02,17 "intermediate_size": 4864,18 "label2id": {19 "Correct": 0,20 "Incorrect": 2,21 "Partiellement correct": 122 },23 "layer_types": [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 ],49 "max_position_embeddings": 32768,50 "max_window_layers": 24,51 "model_type": "qwen2",52 "num_attention_heads": 14,53 "num_hidden_layers": 24,54 "num_key_value_heads": 2,55 "pad_token_id": 151643,56 "rms_norm_eps": 1e-06,57 "rope_parameters": {58 "rope_theta": 1000000.0,59 "rope_type": "default"60 },61 "sliding_window": null,62 "tie_word_embeddings": true,63 "transformers_version": "5.16.1",64 "use_cache": false,65 "use_mrope": false,66 "use_sliding_window": false,67 "vocab_size": 15193668}69 