Hugging Face's logo

tensorblock
/
Poro-34B-chat-GGUF

GGUF
Finnish
English
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
Poro-34B-chat-GGUF / README.md
morriszms's picture
morriszms
Update README.md
c4a5189 verified
preview code
|
raw
history blame contribute delete
4.66 kB
metadata
license: apache-2.0
datasets:
  - LumiOpen/instruction-collection-fin
language:
  - fi
  - en
base_model: LumiOpen/Poro-34B-chat
tags:
  - TensorBlock
  - GGUF
TensorBlock

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

LumiOpen/Poro-34B-chat - GGUF

This repo contains GGUF format model files for LumiOpen/Poro-34B-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
Poro-34B-chat-Q2_K.gguf Q2_K 12.491 GB smallest, significant quality loss - not recommended for most purposes
Poro-34B-chat-Q3_K_S.gguf Q3_K_S 14.415 GB very small, high quality loss
Poro-34B-chat-Q3_K_M.gguf Q3_K_M 17.232 GB very small, high quality loss
Poro-34B-chat-Q3_K_L.gguf Q3_K_L 18.776 GB small, substantial quality loss
Poro-34B-chat-Q4_0.gguf Q4_0 18.647 GB legacy; small, very high quality loss - prefer using Q3_K_M
Poro-34B-chat-Q4_K_S.gguf Q4_K_S 18.790 GB small, greater quality loss
Poro-34B-chat-Q4_K_M.gguf Q4_K_M 20.899 GB medium, balanced quality - recommended
Poro-34B-chat-Q5_0.gguf Q5_0 22.630 GB legacy; medium, balanced quality - prefer using Q4_K_M
Poro-34B-chat-Q5_K_S.gguf Q5_K_S 22.630 GB large, low quality loss - recommended
Poro-34B-chat-Q5_K_M.gguf Q5_K_M 24.320 GB large, very low quality loss - recommended
Poro-34B-chat-Q6_K.gguf Q6_K 26.861 GB very large, extremely low quality loss
Poro-34B-chat-Q8_0.gguf Q8_0 34.785 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/Poro-34B-chat-GGUF --include "Poro-34B-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/Poro-34B-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'