Instructions to use khrisyu/single_node_run-step-486 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use khrisyu/single_node_run-step-486 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, Qwen2ForClassifier tokenizer = AutoTokenizer.from_pretrained("khrisyu/single_node_run-step-486") model = Qwen2ForClassifier.from_pretrained("khrisyu/single_node_run-step-486", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from khrisyu/single_node_run-step-486: direct link, hf CLI and curl.
- Browser
- Download file 1.5 kB
-
https://huggingface.co/khrisyu/single_node_run-step-486/resolve/main/config.json
- Command line
-
hf download hf://khrisyu/single_node_run-step-486/config.json
-
curl -L -o config.json https://huggingface.co/khrisyu/single_node_run-step-486/resolve/main/config.json
1.5 kB
| { | |
| "architectures": [ | |
| "Qwen2ForClassifier" | |
| ], | |
| "attention_dropout": 0.05, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8960, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "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": 21, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "use_cache": false, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |