Translation
Transformers
Safetensors
gemma3_text
text-generation
wmt26
model-compression
machine-translation
gemma
compressed-tensors
vllm
text-generation-inference
Instructions to use soksof/gemma-3-12b-wmt26-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use soksof/gemma-3-12b-wmt26-int4 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="soksof/gemma-3-12b-wmt26-int4")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("soksof/gemma-3-12b-wmt26-int4") model = AutoModelForCausalLM.from_pretrained("soksof/gemma-3-12b-wmt26-int4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4b55b8b7b7f6d0404ac8ed8da4b3861e8e9bc36d74406425f879f2a0a78a8a0f
- Size of remote file:
- 33.4 MB
- SHA256:
- 9bb63c355e7589f305f785b4cd16398ddcb08848c7e7a0f315a3b764aaec032f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.