CodeLlama 7B
PulseAugur coverage of CodeLlama 7B — every cluster mentioning CodeLlama 7B across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New dataset tests how adversarial comments fool LLM code reviewers
A new dataset called CommentInject has been released to test how adversarial code comments can influence LLM code reviewers. The dataset contains 30 vulnerable Python functions across various CWE categories, with commen…
-
New methods boost LLM inference speed and cost-efficiency · 4 sources tracked
Researchers have developed new techniques to optimize Large Language Model (LLM) inference, focusing on efficiency and cost-effectiveness. One approach, Parallel Prompting, significantly speeds up inference for workload…
-
LLM code reviewers misleadingly ranked by detection rate alone
A recent study evaluated 16 open-source LLM code reviewers using 180 Python snippets across nine cryptographic misuse classes. The research found that relying solely on the true positive rate (TPR) for detecting vulnera…
-
New AI framework trains code models to self-correct security flaws
Researchers have developed a novel framework called Tree Self-Play (TSP) to address the inherent security vulnerabilities in large language models trained on code. Current methods like supervised fine-tuning and reinfor…
-
New LLM technique enhances secure code generation by learning from mistakes
Researchers have developed a new framework called Tree-like Self-Play (TSP) to improve the security of code generated by Large Language Models (LLMs). TSP reframes code generation as a sequential decision process, allow…
-
Guides detail local LLM setup with llama.cpp and Ollama
This series of guides details how to set up and run large language models (LLMs) locally on Linux systems. It covers framework comparisons, focusing on llama.cpp and Ollama, and provides step-by-step installation instru…
-
New MultiVul framework uses multimodal LLMs to boost software vulnerability detection
Researchers have developed MultiVul, a novel multimodal framework designed to enhance software vulnerability detection by integrating source code with accompanying comments. This approach addresses limitations of single…
-
Replit releases open-source code model V1.5 3B on Hugging Face
Replit has released its new code generation language model, Replit Code V1.5 3B, on Hugging Face. This model is trained on a massive dataset of permissively licensed code and publicly available developer content, aiming…