Instructions to use ModelSpace/GemmaX2-28-9B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModelSpace/GemmaX2-28-9B-v0.1 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="ModelSpace/GemmaX2-28-9B-v0.1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ModelSpace/GemmaX2-28-9B-v0.1") model = AutoModelForCausalLM.from_pretrained("ModelSpace/GemmaX2-28-9B-v0.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from ModelSpace/GemmaX2-28-9B-v0.1: direct link, hf CLI and curl.
- Browser
- Download file 168 Bytes
-
https://huggingface.co/ModelSpace/GemmaX2-28-9B-v0.1/resolve/2650402b9d0b41d1885976c2f1456c4f39c1663e/generation_config.json
- Command line
-
hf download hf://ModelSpace/GemmaX2-28-9B-v0.1@2650402b9d0b41d1885976c2f1456c4f39c1663e/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/ModelSpace/GemmaX2-28-9B-v0.1/resolve/2650402b9d0b41d1885976c2f1456c4f39c1663e/generation_config.json
168 Bytes
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 2, | |
| "cache_implementation": "hybrid", | |
| "eos_token_id": 1, | |
| "pad_token_id": 0, | |
| "transformers_version": "4.44.2" | |
| } | |