Hugging Face's logo

TeeZee
/
Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Inference Endpoints
Model card Files Community

TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1

Precise recipe used by Upstage to create SOLAR was applied to https://huggingface.co./speakleash/Bielik-7B-Instruct-v0.1 *(just merge, no finetuning)

Results

  • model is still coherent in Polish language, even without finetuning after merge

  • instruct mode works in ooba without issues

  • model is censored and aligned

  • seems that this model scores highest amongst all versions of original Bielik models, further finetunig should improve results even more.

    imgage/png

  • on dedicated to Polish speaking LLM leaderboards, its 2nd, just behind instruct version used for this merge, and thats to be expected when applying DUS merge - very small quality loss.

Polish LLMs leaderboards

  • overall it seems like a good base for further finetunig in Polish language.
Downloads last month
2,229
Safetensors
Model size
10.7B params
Tensor type
BF16
·
Inference Examples
Text Generation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1

Quantizations
2 models

Collection including TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1