This is a quantized variant of google/translategemma-4b-it with templating for vLLM.

Essentially a fuse between https://huggingface.co/kaitchup/translategemma-4b-it-FP8-Dynamic (model) and https://huggingface.co/Infomaniak-AI/vllm-translategemma-4b-it (prompt template & configs).

Chat Template

Format: <<<source>>>{source_lang}<<<target>>>{target_lang}<<<text>>>{text_to_translate}

If you need to provide a custom prompt input

Format: <<<custom>>>{text}

Downloads last month
73
Safetensors
Model size
4B params
Tensor type
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ViralityLeo/vllm-translategemma-4b-it-FP8-Dynamic

Quantized
(1)
this model

Dataset used to train ViralityLeo/vllm-translategemma-4b-it-FP8-Dynamic