Tag

#code-llm

Every item tagged code-llm, newest first.

3 items

Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs

The LiveCodeBench leaderboard evaluates code LLMs on a holistic set of tasks without contamination, providing a more accurate assessment of their performance. It aims to help builders compare and improve code generation models. The leaderboard is open and accessible on the Hugging Face platform.

Key takeaways

LiveCodeBench evaluates code LLMs on diverse tasks without contamination.
Leaderboard is open and accessible on Hugging Face.
Helps builders compare and improve code generation models.

HHugging Face Blog#code-llm #benchmarks #evaluation

modelsApr 9

CodeGemma - an official Google release for code LLMs

Google released CodeGemma, a family of code generation models. The open-weights models come in 2B and 7B parameter sizes. You can use them for code completion, generation, and understanding tasks. CodeGemma targets developers who want to integrate code LLMs into their tools and workflows.

Key takeaways

CodeGemma models are open-weights and available in 2B and 7B sizes.
Targets code completion, generation, and understanding tasks.
Developed by Google for use in developer tools and workflows.

HHugging Face Blog#open-source #code-llm #google

modelsMay 4

StarCoder: A State-of-the-Art LLM for Code

BigCode released StarCoder, a 1B parameter LLM for code generation that matches or exceeds performance of larger models like PaLM-540B and AlphaCode on several benchmarks. StarCoder is available open-source under an Apache 2.0 license. You can use it for research and commercial applications. The model's performance and licensing make it an attractive option for builders looking for a capable, open code generation model.

Key takeaways

1B parameter model outperforms larger models like PaLM-540B.
Available open-source under Apache 2.0 license.
Suitable for both research and commercial use.

HHugging Face Blog#open-source #code-llm #benchmarks