Instructions to use ModelSpace/GemmaX2-28-2B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModelSpace/GemmaX2-28-2B-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/GemmaX2-28-2B-v0.1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ModelSpace/GemmaX2-28-2B-v0.1") model = AutoModelForCausalLM.from_pretrained("ModelSpace/GemmaX2-28-2B-v0.1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Faulty generation_config.json
#5
by ojo - opened
Your generation_config.json has a bad comma, which leads to problems when reading it:
{
"_from_model_config": true,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": 1,
"pad_token_id": 0,
"transformers_version": "4.45.0"๏ผ<- replace this "comma" with ,
"max_new_tokens": 512
}