Here’s my list: 1. Transformers + TRL – for fine-tuning/ RL on smol LLMs
2. vLLM/ MLX/ llama.cpp for serving them locally – fun for local projects
3. Take it one step further with transformers.js w/ WebGPU backend
4. For remote LLMs w/ agents – OpenAI Agents SDK is pretty dope
OPEN SOURCE
-
Fine-tuning and Serving LLMs: Essential Tools and Frameworks
By
–
-
Hugging Face Launches Fast Dataset Duplication Feature with Xet
By
–
We heard your feedback Killer new feature on @huggingface = duplicate any dataset to your account. Thanks to Xet, duplicating a 1TB dataset takes 2 seconds HF is going to be the best platform for large data storage
-
Mistral Large 3 tops Code Arena
By
–
Mistral Large 3 became a top 1 open source model on the Code Arena! Codestral in a few days?
-
Mistral Large 3 Tops Open Source Coding Model Leaderboard
By
–
Mistral Large 3 debuts as the #1 open source coding model on the @arena leaderboard. We'd love for you to try it! More on coding in a few days… 👀
→ View original post on X — @arthurmensch, 2025-12-04 14:00 UTC
-
GitHub graveyard: abandoned repos and half-finished projects
By
–
lmao – the graveyard of empty GH repos/ half assed projects disagree strongly
-
Google Adds Model Selector to NotebookLM
By
–
Google is working on a model selector for NotebookLM so you can switch between Flash and Pro models if needed.
-
BrowseSafe Open-Source Tool Hardens Autonomous Agents Against Prompt Injection
By
–
BrowseSafe and BrowseSafe-Bench are fully open-source. Any developer building autonomous agents can immediately harden their systems against prompt injection. Read more:
-
BrowseSafe: Open-Source Model Prevents Malicious Prompt Injections
By
–
Today we're releasing BrowseSafe and BrowseSafe-Bench: an open-source detection model and benchmark to catch and prevent malicious prompt-injection instructions in real-time.