←Search results

Search “Hugging Face”

By relevance · Total 1193 results Clear search

Tuesday

Monday

Thursday

  2. Hugging Face

    Training a coding model to paint watercolors with TRL and OpenEnv

    A Hugging Face blog post introduces a project that uses TRL and OpenEnv to train a coding model to paint watercolors: the model outputs about 150 lines of JavaScript code and paints via the p5.brush library, and the prompt allows only 10 of the library's 47 methods. The reward is jointly given by the HPSv3 open 7B preference model and a Qwen3-VL-30B-A3B-Instruct pairwise judge, which compares candidate paintings with 4 randomly drawn reference images; three runs with different weight ratios were trained in total.

    A Hugging Face blog post introduces a project that uses TRL and OpenEnv to train a coding model to paint watercolors: the model outputs about 150 lines of JavaScript code and paints via the p5.brush library, and the prompt allows only 10 of the library's 47 methods. The reward is jointly given by the HPSv3 open 7B preference model and a Qwen3-VL-30B-A3B-Instruct pairwise judge, which compares candidate paintings with 4 randomly drawn reference images; three runs with different weight ratios were

    Matched fieldsSummary

    #lab#Tutorials / practice#English text is being prepared.#Open-source ecosystem

Tuesday

Saturday

Friday

  3. Tencent HunyuanSelected

    Tencent Hunyuan releases Hy4 preview, 770B parameters, 49B activated, 1M context

    Tencent Hunyuan releases Hy4 preview, with 770B total parameters, 49B activated, and support for 1M context, positioned for productivity scenarios and the open-source frontier, and emphasizing stable and affordable pricing. The official announcement also provides blog, Hugging Face, and GitHub entry points, and invites users to give feedback on issues.

    Matched fieldsSummary

    #company#Model releases#Open-source ecosystem#English text is being prepared.

Thursday

Wednesday

Tuesday

Friday

Thursday

Wednesday