Downloads · 30 days
967
14% of all-time downloads
MassivDash/Gemma-4-typescript-coder
Gemma-4-typescript-coder is a machine learning model from MassivDash. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a specialized fine-tune of Gemma 4, engineered for TypeScript-centric web development, strict type safety, and modern full-stack architectures. It was trained using Unsloth Studio for maximum efficiency…
Downloads · 30 days
967
14% of all-time downloads
All-time downloads
7.2K
Public
Repo size
28.6 GB
Likes
6
Public
Click a slice to open those files.
.gguf23.7 GB · 100%
From the Hugging Face model README
This model is a specialized fine-tune of Gemma 4, engineered for TypeScript-centric web development, strict type safety, and modern full-stack architectures. It was trained using Unsloth Studio for maximum efficiency and precision.
This fine-tune specializes in:
A major shout-out to mhhmm for the typescript-instruct-20k dataset. This robust collection of instructions allowed the model to grasp the nuances of the TypeScript ecosystem effectively.
The model is provided in GGUF format, compatible with llama.cpp.
Example usage:
llama-cli -hf MassivDash/Gemma-4-typescript-coder --jinjallama-mtmd-cli -hf MassivDash/Gemma-4-typescript-coder --jinjagemma-4-e2b-it.Q8_0.ggufgemma-4-e2b-it.BF16-mmproj.ggufImportant: Ollama currently requires a unified blob for vision models.
To use this with Ollama:
Modelfile is in the same directory as the merged BF16 model.ollama create model_name -f ./ModelfileFor more insights on AI development and fine-tuning, visit my blog: 👉 spaceout.pl
This model was trained 2x faster with Unsloth