2025-12-05
We used Claude Code to train open LLMs. Check out the tutorial. basically, we plugged HF skills into claude code and it was able to train LLMs end-to-end. Best thing, this works on all major coding agents: Codex, Cursor, and Gemini CLI. - You tell the agent to fine-tune a model [image]
Hugging Face
Hugging Face details how it used its new tool, Skills, to fine tune an LLM using Claude, including for writing scripts, submitting jobs to cloud GPUs, and more
We gave Claude the ability to fine-tune language models using a new tool called Hugging Face Skills. X: @ben_burtenshaw , @donvito , @ben_burtenshaw , @arig23498 , and @ben_burtens...
just to clarify, yes! claude code is contributing to open source ai.
Hugging Face
Hugging Face details how it used its new tool, Skills, to fine tune an LLM using Claude, including for writing scripts, submitting jobs to cloud GPUs, and more
We gave Claude the ability to fine-tune language models using a new tool called Hugging Face Skills. X: @ben_burtenshaw , @donvito , @ben_burtenshaw , @arig23498 , and @ben_burtens...
@ivibecode We actually have a benchmarking skill, that evaluates models. We're going to do another post on that when it's finished.
Hugging Face
Hugging Face details how it used its new tool, Skills, to fine tune an LLM using Claude, including for writing scripts, submitting jobs to cloud GPUs, and more
We gave Claude the ability to fine-tune language models using a new tool called Hugging Face Skills. X: @ben_burtenshaw , @donvito , @ben_burtenshaw , @arig23498 , and @ben_burtens...