metadata
license: mit
license_link: https://huggingface.co/microsoft/wavecoder-ultra-6.7b/blob/main/LICENSE
language:
- en
library_name: transformers
datasets:
- humaneval
pipeline_tag: text-generation
tags:
- code
- TensorBlock
- GGUF
metrics:
- code_eval
base_model: microsoft/wavecoder-ultra-6.7b
microsoft/wavecoder-ultra-6.7b - GGUF
This repo contains GGUF format model files for microsoft/wavecoder-ultra-6.7b.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4242.
Our projects
| Forge | |
|---|---|
|
|
| An OpenAI-compatible multi-provider routing layer. | |
| 🚀 Try it now! 🚀 | |
| Awesome MCP Servers | TensorBlock 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 👀 |
<｜begin▁of▁sentence｜>You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
@@ Instruction
{prompt}
@@ Response
Model file specification
| Filename | Quant type | File Size | Description |
|---|---|---|---|
| wavecoder-ultra-6.7b-Q2_K.gguf | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
| wavecoder-ultra-6.7b-Q3_K_S.gguf | Q3_K_S | 2.949 GB | very small, high quality loss |
| wavecoder-ultra-6.7b-Q3_K_M.gguf | Q3_K_M | 3.299 GB | very small, high quality loss |
| wavecoder-ultra-6.7b-Q3_K_L.gguf | Q3_K_L | 3.598 GB | small, substantial quality loss |
| wavecoder-ultra-6.7b-Q4_0.gguf | Q4_0 | 3.826 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| wavecoder-ultra-6.7b-Q4_K_S.gguf | Q4_K_S | 3.857 GB | small, greater quality loss |
| wavecoder-ultra-6.7b-Q4_K_M.gguf | Q4_K_M | 4.082 GB | medium, balanced quality - recommended |
| wavecoder-ultra-6.7b-Q5_0.gguf | Q5_0 | 4.652 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| wavecoder-ultra-6.7b-Q5_K_S.gguf | Q5_K_S | 4.652 GB | large, low quality loss - recommended |
| wavecoder-ultra-6.7b-Q5_K_M.gguf | Q5_K_M | 4.784 GB | large, very low quality loss - recommended |
| wavecoder-ultra-6.7b-Q6_K.gguf | Q6_K | 5.530 GB | very large, extremely low quality loss |
| wavecoder-ultra-6.7b-Q8_0.gguf | Q8_0 | 7.162 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/wavecoder-ultra-6.7b-GGUF --include "wavecoder-ultra-6.7b-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/wavecoder-ultra-6.7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'