Download teacher_checkpoints/clinc_coarse/qwen7b/config.json from DistillationDiffusion/ModelFineTunedCheckpointsReal: direct link, hf CLI and curl.
- Browser
- Download file 1.85 kB
-
https://huggingface.co/DistillationDiffusion/ModelFineTunedCheckpointsReal/resolve/main/teacher_checkpoints/clinc_coarse/qwen7b/config.json
- Command line
-
hf download hf://DistillationDiffusion/ModelFineTunedCheckpointsReal/teacher_checkpoints/clinc_coarse/qwen7b/config.json
-
curl -L -o config.json https://huggingface.co/DistillationDiffusion/ModelFineTunedCheckpointsReal/resolve/main/teacher_checkpoints/clinc_coarse/qwen7b/config.json
1.85 kB
| { | |
| "architectures": [ | |
| "Qwen2ForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "dtype": "float32", | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 3584, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2", | |
| "3": "LABEL_3", | |
| "4": "LABEL_4", | |
| "5": "LABEL_5", | |
| "6": "LABEL_6", | |
| "7": "LABEL_7", | |
| "8": "LABEL_8", | |
| "9": "LABEL_9" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18944, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2, | |
| "LABEL_3": 3, | |
| "LABEL_4": 4, | |
| "LABEL_5": 5, | |
| "LABEL_6": 6, | |
| "LABEL_7": 7, | |
| "LABEL_8": 8, | |
| "LABEL_9": 9 | |
| }, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 28, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": 151643, | |
| "problem_type": "single_label_classification", | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.6", | |
| "use_cache": false, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |