morriszms's picture
Update README.md
0a095ee verified
|
raw
history blame
5.15 kB
metadata
license: apache-2.0
language:
  - pl
tags:
  - TensorBlock
  - GGUF
base_model: piotr-ai/polanka-qwen2-3b-v0.3-chat
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

piotr-ai/polanka-qwen2-3b-v0.3-chat - GGUF

This repo contains GGUF format model files for piotr-ai/polanka-qwen2-3b-v0.3-chat.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename Quant type File Size Description
polanka-qwen2-3b-v0.3-chat-Q2_K.gguf Q2_K 1.381 GB smallest, significant quality loss - not recommended for most purposes
polanka-qwen2-3b-v0.3-chat-Q3_K_S.gguf Q3_K_S 1.573 GB very small, high quality loss
polanka-qwen2-3b-v0.3-chat-Q3_K_M.gguf Q3_K_M 1.676 GB very small, high quality loss
polanka-qwen2-3b-v0.3-chat-Q3_K_L.gguf Q3_K_L 1.771 GB small, substantial quality loss
polanka-qwen2-3b-v0.3-chat-Q4_0.gguf Q4_0 1.929 GB legacy; small, very high quality loss - prefer using Q3_K_M
polanka-qwen2-3b-v0.3-chat-Q4_K_S.gguf Q4_K_S 1.937 GB small, greater quality loss
polanka-qwen2-3b-v0.3-chat-Q4_K_M.gguf Q4_K_M 2.012 GB medium, balanced quality - recommended
polanka-qwen2-3b-v0.3-chat-Q5_0.gguf Q5_0 2.263 GB legacy; medium, balanced quality - prefer using Q4_K_M
polanka-qwen2-3b-v0.3-chat-Q5_K_S.gguf Q5_K_S 2.263 GB large, low quality loss - recommended
polanka-qwen2-3b-v0.3-chat-Q5_K_M.gguf Q5_K_M 2.307 GB large, very low quality loss - recommended
polanka-qwen2-3b-v0.3-chat-Q6_K.gguf Q6_K 2.619 GB very large, extremely low quality loss
polanka-qwen2-3b-v0.3-chat-Q8_0.gguf Q8_0 3.391 GB very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/polanka-qwen2-3b-v0.3-chat-GGUF --include "polanka-qwen2-3b-v0.3-chat-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/polanka-qwen2-3b-v0.3-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'