Hugging Face's logo

tensorblock
/
33x-coder-GGUF

Transformers
GGUF
English
Code Generation
TensorBlock
GGUF
Model card Files Community
33x-coder-GGUF / README.md
morriszms's picture
morriszms
Update README.md
2eb1170 verified
preview code
|
raw
history blame contribute delete
5.44 kB
metadata
language:
  - en
metrics:
  - code_eval
library_name: transformers
tags:
  - Code Generation
  - TensorBlock
  - GGUF
datasets:
  - andersonbcdefg/synthetic_retrieval_tasks
  - ise-uiuc/Magicoder-Evol-Instruct-110K
license: apache-2.0
base_model: senseable/33x-coder
TensorBlock

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

senseable/33x-coder - GGUF

This repo contains GGUF format model files for senseable/33x-coder.

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

Our projects

Awesome MCP Servers TensorBlock Studio
Project A Project B
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

Model file specification

Filename Quant type File Size Description
33x-coder-Q2_K.gguf Q2_K 12.356 GB smallest, significant quality loss - not recommended for most purposes
33x-coder-Q3_K_S.gguf Q3_K_S 14.422 GB very small, high quality loss
33x-coder-Q3_K_M.gguf Q3_K_M 16.092 GB very small, high quality loss
33x-coder-Q3_K_L.gguf Q3_K_L 17.560 GB small, substantial quality loss
33x-coder-Q4_0.gguf Q4_0 18.819 GB legacy; small, very high quality loss - prefer using Q3_K_M
33x-coder-Q4_K_S.gguf Q4_K_S 18.943 GB small, greater quality loss
33x-coder-Q4_K_M.gguf Q4_K_M 19.941 GB medium, balanced quality - recommended
33x-coder-Q5_0.gguf Q5_0 22.958 GB legacy; medium, balanced quality - prefer using Q4_K_M
33x-coder-Q5_K_S.gguf Q5_K_S 22.958 GB large, low quality loss - recommended
33x-coder-Q5_K_M.gguf Q5_K_M 23.536 GB large, very low quality loss - recommended
33x-coder-Q6_K.gguf Q6_K 27.356 GB very large, extremely low quality loss
33x-coder-Q8_0.gguf Q8_0 35.431 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/33x-coder-GGUF --include "33x-coder-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/33x-coder-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'