lmstudio-community/wavecoder-ultra-6.7b-GGUF

💫 Community Model> wavecoder-ultra-6.7b by Microsoft

👾 LM Studio Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on Discord.

Model creator: Microsoft
Original model: wavecoder-ultra-6.7b
GGUF quantization: provided by bartowski based on llama.cpp release b2675

Model Summary:

WaveCoder ultra is a coding model created with 'Widepread And Versatile Enhanced' instruction tuning. It has exceptional generalization ability across different code-related tasks and has a high efficiency in generation.
This model should be used exclusively for coding, and will follow instructions for code generation.

Prompt Template:

Choose the Alpaca preset in your LM Studio.

Under the hood, the model will see a prompt that's formatted like so:

Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction: {prompt}
### Response:

Use case and examples

WaveCoder ultra is fine tuned for code-related instruction following tasks, including code generation, summarization, repair, and translation.

Code Generation

Code Summarization

Code Repair

Code Translation

Technical Details

The WaveCoder series of models is the result of a 'Widespread And Versatile Enchanced' (WAVE) instruction tuning with a highly refined dataset.

Their 'CodeOcean' consists of 20,000 instruction instances across the 4 code-related tasks (generation, summarization, repair, translation) with instructions generated by GPT-3.5-turbo.

To create this dataset, the team used existing raw code from GitHub CodeSearchNet, filtering for quality and diversity, then used a 'novel LLM-based Generator-Discriminator Framework' which involves generating supervised instruction data from the unsupervised open source code.

For further details and benchmarks, check out their arXiv paper here

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

🙏 Special thanks to Kalomaze for his dataset (linked here) that was used for calculating the imatrix for these quants, which improves the overall quality!

Disclaimers

LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.