Instructions to use winninghealth/WiNGPT-Babel-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use winninghealth/WiNGPT-Babel-2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="winninghealth/WiNGPT-Babel-2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("winninghealth/WiNGPT-Babel-2") model = AutoModelForCausalLM.from_pretrained("winninghealth/WiNGPT-Babel-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from winninghealth/WiNGPT-Babel-2: direct link, hf CLI and curl.
- Browser
- Download file 167 Bytes
-
https://huggingface.co/winninghealth/WiNGPT-Babel-2/resolve/main/generation_config.json
- Command line
-
hf download hf://winninghealth/WiNGPT-Babel-2/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/winninghealth/WiNGPT-Babel-2/resolve/main/generation_config.json
167 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "eos_token_id": 1, | |
| "pad_token_id": 0, | |
| "transformers_version": "4.45.0" | |
| } |