vansin
vansin
AI & ML interests
None yet
Recent Activity
commented on
a paper
4 days ago
Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for
Large Language Models
commented on
a paper
4 days ago
FLAME: A Federated Learning Benchmark for Robotic Manipulation
commented on
a paper
4 days ago
Benchmarking Large Language Models for Multi-Language Software
Vulnerability Detection
Organizations
vansin's activity
reacted to
their
post with 🚀🔥
3 months ago
reacted to
their
post with 👀
3 months ago
Post
1270
Amazing !!!! test Post
reacted to
loubnabnl's
post with 🔥
3 months ago
Post
2969
Making SmolLM2 reproducible: open-sourcing our training & evaluation toolkit 🛠️ https://github.com/huggingface/smollm/
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?
- Pre-training code with nanotron
- Evaluation suite with lighteval
- Synthetic data generation using distilabel (powers our new SFT dataset HuggingFaceTB/smoltalk)
- Post-training scripts with TRL & the alignment handbook
- On-device tools with llama.cpp for summarization, rewriting & agents
Apache 2.0 licensed. V2 pre-training data mix coming soon!
Which other tools should we add next?