GGUF
English
TensorBlock
GGUF
Inference Endpoints
TensorBlock

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

OpenAssistant/codellama-13b-oasst-sft-v10 - GGUF

This repo contains GGUF format model files for OpenAssistant/codellama-13b-oasst-sft-v10.

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
codellama-13b-oasst-sft-v10-Q2_K.gguf Q2_K 4.521 GB smallest, significant quality loss - not recommended for most purposes
codellama-13b-oasst-sft-v10-Q3_K_S.gguf Q3_K_S 5.271 GB very small, high quality loss
codellama-13b-oasst-sft-v10-Q3_K_M.gguf Q3_K_M 5.903 GB very small, high quality loss
codellama-13b-oasst-sft-v10-Q3_K_L.gguf Q3_K_L 6.454 GB small, substantial quality loss
codellama-13b-oasst-sft-v10-Q4_0.gguf Q4_0 6.860 GB legacy; small, very high quality loss - prefer using Q3_K_M
codellama-13b-oasst-sft-v10-Q4_K_S.gguf Q4_K_S 6.914 GB small, greater quality loss
codellama-13b-oasst-sft-v10-Q4_K_M.gguf Q4_K_M 7.326 GB medium, balanced quality - recommended
codellama-13b-oasst-sft-v10-Q5_0.gguf Q5_0 8.356 GB legacy; medium, balanced quality - prefer using Q4_K_M
codellama-13b-oasst-sft-v10-Q5_K_S.gguf Q5_K_S 8.356 GB large, low quality loss - recommended
codellama-13b-oasst-sft-v10-Q5_K_M.gguf Q5_K_M 8.596 GB large, very low quality loss - recommended
codellama-13b-oasst-sft-v10-Q6_K.gguf Q6_K 9.946 GB very large, extremely low quality loss
codellama-13b-oasst-sft-v10-Q8_0.gguf Q8_0 12.882 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/codellama-13b-oasst-sft-v10-GGUF --include "codellama-13b-oasst-sft-v10-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/codellama-13b-oasst-sft-v10-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
Downloads last month
120
GGUF
Model size
13B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

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

Model tree for tensorblock/codellama-13b-oasst-sft-v10-GGUF

Quantized
(4)
this model

Datasets used to train tensorblock/codellama-13b-oasst-sft-v10-GGUF