emre570
/

gemma-7b-us-minecraft

Model card Files Files and versions

Gemma 1.1 7B Instruct Minecraft Adapter Model

Updated Version

This model is fine-tuned from Unsloth's Gemma 1.1 7B Instruct quantized model with naklecha's Minecraft Question-Answer dataset. Fine-tuned with first 100k rows from dataset with 1 epoch, it took around 2 hours 20 minutes with NVIDIA RTX 4090.

Model can now generate some good answers. But sometimes it can generate inappropriate answers. I think this problem is based on lack of data.

Important Notes

Model sometimes generates answers with no meanings. I am currently investigating this. This process can be long since I am a beginner in this field. If you have any suggestions, feel free to say it on model's Community page.
Model is using bitsandbytes so use it with a CUDA supported GPU.

Downloads last month: 15

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for emre570/gemma-7b-us-minecraft

Base model

unsloth/gemma-1.1-7b-it-bnb-4bit

Adapter

(4)

this model

Dataset used to train emre570/gemma-7b-us-minecraft