karakuri-ai/karakuri-lm-8x7b-instruct-v0.1 - GGUF

This repo contains GGUF format model files for karakuri-ai/karakuri-lm-8x7b-instruct-v0.1.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.

Our projects

Forge
Forge Project
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
MCP Servers	Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

## Prompt template

<s><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{system_prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>{prompt}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><attributes>helpfulness: 4 correctness: 4 coherence: 4 complexity: 4 verbosity: 4 quality: 4 toxicity: 0 humor: 0 creativity: 0</attributes>

Model file specification

Filename	Quant type	File Size	Description
karakuri-lm-8x7b-instruct-v0.1-Q2_K.gguf	Q2_K	17.312 GB	smallest, significant quality loss - not recommended for most purposes
karakuri-lm-8x7b-instruct-v0.1-Q3_K_S.gguf	Q3_K_S	20.433 GB	very small, high quality loss
karakuri-lm-8x7b-instruct-v0.1-Q3_K_M.gguf	Q3_K_M	22.547 GB	very small, high quality loss
karakuri-lm-8x7b-instruct-v0.1-Q3_K_L.gguf	Q3_K_L	24.170 GB	small, substantial quality loss
karakuri-lm-8x7b-instruct-v0.1-Q4_0.gguf	Q4_0	26.444 GB	legacy; small, very high quality loss - prefer using Q3_K_M
karakuri-lm-8x7b-instruct-v0.1-Q4_K_S.gguf	Q4_K_S	26.746 GB	small, greater quality loss
karakuri-lm-8x7b-instruct-v0.1-Q4_K_M.gguf	Q4_K_M	28.449 GB	medium, balanced quality - recommended
karakuri-lm-8x7b-instruct-v0.1-Q5_0.gguf	Q5_0	32.232 GB	legacy; medium, balanced quality - prefer using Q4_K_M
karakuri-lm-8x7b-instruct-v0.1-Q5_K_S.gguf	Q5_K_S	32.232 GB	large, low quality loss - recommended
karakuri-lm-8x7b-instruct-v0.1-Q5_K_M.gguf	Q5_K_M	33.230 GB	large, very low quality loss - recommended
karakuri-lm-8x7b-instruct-v0.1-Q6_K.gguf	Q6_K	38.382 GB	very large, extremely low quality loss
karakuri-lm-8x7b-instruct-v0.1-Q8_0.gguf	Q8_0	49.627 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/karakuri-lm-8x7b-instruct-v0.1-GGUF --include "karakuri-lm-8x7b-instruct-v0.1-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/karakuri-lm-8x7b-instruct-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'