TensorBlock

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

karakuri-ai/karakuri-lm-7b-apm-v0.1 - GGUF

This repo contains GGUF format model files for karakuri-ai/karakuri-lm-7b-apm-v0.1.

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
karakuri-lm-7b-apm-v0.1-Q2_K.gguf Q2_K 3.481 GB smallest, significant quality loss - not recommended for most purposes
karakuri-lm-7b-apm-v0.1-Q3_K_S.gguf Q3_K_S 3.982 GB very small, high quality loss
karakuri-lm-7b-apm-v0.1-Q3_K_M.gguf Q3_K_M 4.369 GB very small, high quality loss
karakuri-lm-7b-apm-v0.1-Q3_K_L.gguf Q3_K_L 4.709 GB small, substantial quality loss
karakuri-lm-7b-apm-v0.1-Q4_0.gguf Q4_0 5.012 GB legacy; small, very high quality loss - prefer using Q3_K_M
karakuri-lm-7b-apm-v0.1-Q4_K_S.gguf Q4_K_S 5.046 GB small, greater quality loss
karakuri-lm-7b-apm-v0.1-Q4_K_M.gguf Q4_K_M 5.330 GB medium, balanced quality - recommended
karakuri-lm-7b-apm-v0.1-Q5_0.gguf Q5_0 5.981 GB legacy; medium, balanced quality - prefer using Q4_K_M
karakuri-lm-7b-apm-v0.1-Q5_K_S.gguf Q5_K_S 5.981 GB large, low quality loss - recommended
karakuri-lm-7b-apm-v0.1-Q5_K_M.gguf Q5_K_M 6.145 GB large, very low quality loss - recommended
karakuri-lm-7b-apm-v0.1-Q6_K.gguf Q6_K 7.010 GB very large, extremely low quality loss
karakuri-lm-7b-apm-v0.1-Q8_0.gguf Q8_0 9.078 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-7b-apm-v0.1-GGUF --include "karakuri-lm-7b-apm-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-7b-apm-v0.1-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
746
GGUF
Model size
8.54B params
Architecture
gemma

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for tensorblock/karakuri-lm-7b-apm-v0.1-GGUF

Base model

google/gemma-7b
Quantized
(1)
this model

Datasets used to train tensorblock/karakuri-lm-7b-apm-v0.1-GGUF