QuantPanda

QuantPanda

AI & ML interests

None yet

Recent Activity

liked a model 8 days ago
QuantFactory/HuatuoGPT-o1-7B-GGUF
View all activity

Organizations

None yet

QuantPanda's activity

reacted to MoritzLaurer's post with πŸ˜” about 2 hours ago
view post
Post
2473
FACTS is a great paper from @GoogleDeepMind on measuring the factuality of LLM outputs. You can now download their prompt templates from @huggingface to improve LLM-based fact-checking yourself!

πŸ“ The paper introduces the FACTS Grounding benchmark for evaluating the factuality of LLM outputs.

πŸ€– Fact-checking is automated by an ensemble of LLM judges that verify if a response is fully grounded in a factual reference document.

πŸ§ͺ The authors tested different prompt templates on held-out data to ensure their generalization.

πŸ“š It's highly educational to read these templates to learn how frontier labs design prompts and understand their limitations.

πŸ’Ύ You can now download and reuse these prompt templates via the prompt-templates library!

πŸ”„ The library simplifies sharing prompt templates on the HF hub or locally via standardized YAML files. Let’s make LLM work more transparent and reproducible by sharing more templates like this!

Links πŸ‘‡
- prompt-templates docs: https://moritzlaurer.github.io/prompt_templates/
- all templates on the HF Hub: MoritzLaurer/facts-grounding-prompts
- FACTS paper: https://storage.googleapis.com/deepmind-media/FACTS/FACTS_grounding_paper.pdf
reacted to lewtun's post with πŸ”₯ 8 days ago
view post
Post
3201
I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!

https://x.com/casper_hansen_/status/1875872309996855343

Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!

[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co/blog/ganqu/prime
New activity in FreedomIntelligence/HuatuoGPT-o1-7B 8 days ago

Update

5
#1 opened 8 days ago by
QuantPanda
New activity in deepseek-ai/DeepSeek-V3 8 days ago

Update README.md

1
#37 opened 11 days ago by
TomGrc
reacted to davidberenstein1957's post with πŸš€ 9 days ago
replied to davidberenstein1957's post 9 days ago
view reply

This is the kind of write up that I needed, thank you

GGUF

4
#1 opened 28 days ago by
MikeLightheart