morriszms's picture
Upload folder using huggingface_hub
4c4895a verified
|
raw
history blame
4.47 kB
metadata
tags:
  - generated_from_trainer
  - conversational
  - polish
  - TensorBlock
  - GGUF
license: mit
language:
  - pl
datasets:
  - eryk-mazus/polka-dpo-v1
pipeline_tag: text-generation
inference: false
base_model: eryk-mazus/polka-1.1b-chat
TensorBlock

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

eryk-mazus/polka-1.1b-chat - GGUF

This repo contains GGUF format model files for eryk-mazus/polka-1.1b-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
polka-1.1b-chat-Q2_K.gguf Q2_K 0.429 GB smallest, significant quality loss - not recommended for most purposes
polka-1.1b-chat-Q3_K_S.gguf Q3_K_S 0.494 GB very small, high quality loss
polka-1.1b-chat-Q3_K_M.gguf Q3_K_M 0.539 GB very small, high quality loss
polka-1.1b-chat-Q3_K_L.gguf Q3_K_L 0.580 GB small, substantial quality loss
polka-1.1b-chat-Q4_0.gguf Q4_0 0.625 GB legacy; small, very high quality loss - prefer using Q3_K_M
polka-1.1b-chat-Q4_K_S.gguf Q4_K_S 0.628 GB small, greater quality loss
polka-1.1b-chat-Q4_K_M.gguf Q4_K_M 0.654 GB medium, balanced quality - recommended
polka-1.1b-chat-Q5_0.gguf Q5_0 0.748 GB legacy; medium, balanced quality - prefer using Q4_K_M
polka-1.1b-chat-Q5_K_S.gguf Q5_K_S 0.748 GB large, low quality loss - recommended
polka-1.1b-chat-Q5_K_M.gguf Q5_K_M 0.763 GB large, very low quality loss - recommended
polka-1.1b-chat-Q6_K.gguf Q6_K 0.879 GB very large, extremely low quality loss
polka-1.1b-chat-Q8_0.gguf Q8_0 1.138 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/polka-1.1b-chat-GGUF --include "polka-1.1b-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/polka-1.1b-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'