2,685 Downloads Updated 1 year ago
Name
9 models
bielik-7b-instruct-v0.1-gguf:latest
4.1GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q3_K_S
3.2GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q3_K_M
3.5GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q3_K_L
3.8GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q4_K_S
4.1GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q5_K_S
5.0GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q5_K_M
5.1GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q6_K
5.9GB · 4K context window · Text · 1 year ago
bielik-7b-instruct-v0.1-gguf:Q8_0
7.7GB · 4K context window · Text · 1 year ago
ollama run SpeakLeash/bielik-7b-instruct-v0.1-gguf
for other quants use Tags, e.g.
ollama run SpeakLeash/bielik-7b-instruct-v0.1-gguf:Q8_0
To create your own version or with specific temperature or other args use docs:
https://github.com/ollama/ollama/blob/main/docs/modelfile.md
This repo contains GGUF format model files for SpeakLeash’s Bielik-7B-Instruct-v0.1. https://huggingface.co/speakleash/Bielik-7B-Instruct-v0.1-GGUF
DISCLAIMER: Be aware that quantised models show reduced response quality and possible hallucinations!
Model description:
Developed by: SpeakLeash
Language: Polish
Model type: causal decoder-only
Quant from: Bielik-7B-Instruct-v0.1
Finetuned from: Bielik-7B-v0.1
License: CC BY NC 4.0 (non-commercial use)
Model ref: speakleash:e38140bea0d48f1218540800bbc67e89
Website: https://speakleash.org Hugging Face: https://huggingface.co/speakleash