TensorBlock

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

CohereForAI/aya-23-8B - GGUF

This repo contains GGUF format model files for CohereForAI/aya-23-8B.

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

Prompt template

<BOS_TOKEN><|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|>

Model file specification

Filename Quant type File Size Description
aya-23-8B-Q2_K.gguf Q2_K 3.438 GB smallest, significant quality loss - not recommended for most purposes
aya-23-8B-Q3_K_S.gguf Q3_K_S 3.871 GB very small, high quality loss
aya-23-8B-Q3_K_M.gguf Q3_K_M 4.225 GB very small, high quality loss
aya-23-8B-Q3_K_L.gguf Q3_K_L 4.528 GB small, substantial quality loss
aya-23-8B-Q4_0.gguf Q4_0 4.797 GB legacy; small, very high quality loss - prefer using Q3_K_M
aya-23-8B-Q4_K_S.gguf Q4_K_S 4.829 GB small, greater quality loss
aya-23-8B-Q4_K_M.gguf Q4_K_M 5.057 GB medium, balanced quality - recommended
aya-23-8B-Q5_0.gguf Q5_0 5.670 GB legacy; medium, balanced quality - prefer using Q4_K_M
aya-23-8B-Q5_K_S.gguf Q5_K_S 5.670 GB large, low quality loss - recommended
aya-23-8B-Q5_K_M.gguf Q5_K_M 5.804 GB large, very low quality loss - recommended
aya-23-8B-Q6_K.gguf Q6_K 6.597 GB very large, extremely low quality loss
aya-23-8B-Q8_0.gguf Q8_0 8.541 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/aya-23-8B-GGUF --include "aya-23-8B-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/aya-23-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
701
GGUF
Model size
8.03B params
Architecture
command-r

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference API
Inference API (serverless) has been turned off for this model.

Model tree for tensorblock/aya-23-8B-GGUF

Quantized
(15)
this model