We fine-tuned Llama and got 4.2x Sonnet 3.5 accuracy for code generation (finecodex.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of finecodex.com: We fine-tuned Llama and got 4.2x Sonnet 3.5 accuracy for code generation

First screen, captured 1 year ago.

Looks similar

Screenshot of functiontrace.com: FunctionTrace: Graphical Python Profiler

FunctionTrace: Graphical Python Profiler (functiontrace.com)

107 points by alex_hirner 3 years ago | 28 comments

Screenshot of openlayer.com: Show HN: Openlayer – Test, fix, and improve your ML models

Show HN: Openlayer – Test, fix, and improve your ML models (openlayer.com)

40 points by vikasnair 3 years ago | 8 comments

Screenshot of stagewise.io: Show HN: Stagewise – frontend coding agent for real codebases

Show HN: Stagewise – frontend coding agent for real codebases (stagewise.io)

27 points by glenntws 1 year ago | 12 comments

Screenshot of noodl.net: Noodl is going open source

Noodl is going open source (noodl.net)

33 points by bradrn 3 years ago | 4 comments

Screenshot of reactagent.io: ReactAgent: LLM Agent for React Coding

ReactAgent: LLM Agent for React Coding (reactagent.io)

121 points by omarfarooq 3 years ago | 41 comments

Screenshot of deepseek.com: DeepSeek v2.5 – open-source LLM comparable to GPT-4, but 95% less expensive

DeepSeek v2.5 – open-source LLM comparable to GPT-4, but 95% less expensive (deepseek.com)

149 points by jchook 2 years ago | 41 comments