Downloads · 30 days
6
10% of all-time downloads
TeeZee_-_Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1-4bits
RichardErkhov/TeeZee_-_Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1-4bits
TeeZee_-_Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1-4bits is a text generation model from RichardErkhov. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
63
Public
Parameters
10.9B
6.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.4 GB · 100%
Parameter types
How the weights are stored.
U810.5B · 96%
Try a prompt
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1 - bnb 4bits
- Model creator: https://huggingface.co/TeeZee/
- Original model: https://huggingface.co/TeeZee/Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1/
Original model description:
license: cc-by-nc-4.0
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.
-
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.
- overall it seems like a good base for further finetunig in Polish language.
- Task
- Text Generation
- Library
- transformers
- Type
- mistral
- Created
- May 13, 2024
- Updated
- May 13, 2024