TensorBlock

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

URP/urllm-ko-7b - GGUF

This repo contains GGUF format model files for URP/urllm-ko-7b.

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

Prompt template


Model file specification

Filename Quant type File Size Description
urllm-ko-7b-Q2_K.gguf Q2_K 2.444 GB smallest, significant quality loss - not recommended for most purposes
urllm-ko-7b-Q3_K_S.gguf Q3_K_S 2.839 GB very small, high quality loss
urllm-ko-7b-Q3_K_M.gguf Q3_K_M 3.164 GB very small, high quality loss
urllm-ko-7b-Q3_K_L.gguf Q3_K_L 3.443 GB small, substantial quality loss
urllm-ko-7b-Q4_0.gguf Q4_0 3.666 GB legacy; small, very high quality loss - prefer using Q3_K_M
urllm-ko-7b-Q4_K_S.gguf Q4_K_S 3.695 GB small, greater quality loss
urllm-ko-7b-Q4_K_M.gguf Q4_K_M 3.903 GB medium, balanced quality - recommended
urllm-ko-7b-Q5_0.gguf Q5_0 4.444 GB legacy; medium, balanced quality - prefer using Q4_K_M
urllm-ko-7b-Q5_K_S.gguf Q5_K_S 4.444 GB large, low quality loss - recommended
urllm-ko-7b-Q5_K_M.gguf Q5_K_M 4.567 GB large, very low quality loss - recommended
urllm-ko-7b-Q6_K.gguf Q6_K 5.271 GB very large, extremely low quality loss
urllm-ko-7b-Q8_0.gguf Q8_0 6.827 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/urllm-ko-7b-GGUF --include "urllm-ko-7b-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/urllm-ko-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
27
GGUF
Model size
6.9B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for tensorblock/urllm-ko-7b-GGUF

Base model

URP/urllm-ko-7b
Quantized
(3)
this model