Hugging Face's logo
Agustín Piqueres Lajarín's picture
11 35 58

Agustín Piqueres Lajarín

plaguss
gabrielmbmb's profile picture shuyuej's profile picture Akash20000's profile picture
·

AI & ML interests

None yet

Recent Activity

reacted to lewtun's post with 🔥 5 days ago
This paper (https://huggingface.co/papers/2412.18925) has a really interesting recipe for inducing o1-like behaviour in Llama models: * Iteratively sample CoTs from the model, using a mix of different search strategies. This gives you something like Stream of Search via prompting. * Verify correctness of each CoT using GPT-4o (needed because exact match doesn't work well in medicine where there are lots of aliases) * Use GPT-4o to reformat the concatenated CoTs into a single stream that includes smooth transitions like "hmm, wait" etc that one sees in o1 * Use the resulting data for SFT & RL * Use sparse rewards from GPT-4o to guide RL training. They find RL gives an average ~3 point boost across medical benchmarks and SFT on this data already gives a strong improvement. Applying this strategy to other domains could be quite promising, provided the training data can be formulated with verifiable problems!
liked a Space 7 days ago
data-agents/jupyter-agent
liked a Space 18 days ago
HuggingFaceH4/blogpost-scaling-test-time-compute
View all activity

Articles

Organizations

Hugging Face's profile picture SomosNLP's profile picture Hugging Face H4's profile picture Argilla's profile picture Blog-explorers's profile picture Hugging Face TB Research's profile picture Argilla Explorers's profile picture distilabel-internal-testing's profile picture Data Is Better Together's profile picture LLHF's profile picture SLLHF's profile picture Hugging Quants's profile picture argilla-internal-testing's profile picture Argilla Warehouse's profile picture Hugging Face FineVideo's profile picture smol-explorers's profile picture Hugging Face Science's profile picture Data Is Better Together Contributor's profile picture

plaguss's activity

New activity in argilla/FinePersonas-v0.1 24 days ago

Removing embeddings information to reduce the size of this dataset

3
#6 opened 3 months ago by
alexneakameni
New activity in argilla/FinePersonas-v0.1 3 months ago

noob questions

2
#4 opened 3 months ago by
KarolCodes

How to run the persona-to-persona code?

1
#5 opened 3 months ago by
dimpu01
New activity in argilla/FinePersonas-v0.1 4 months ago

Multimodal Personas

2
#2 opened 4 months ago by
Taylor658
New activity in argilla/magpie-ultra-v0.1 5 months ago

Update README.md
#7 opened 5 months ago by
Sweatydragon1
New activity in plaguss/distilabel-sample-evol-instruct 11 months ago

add distilabel and synthethic tag

1
#2 opened 11 months ago by
davidberenstein1957
New activity in argilla/distilabeled-Marcoro14-7B-slerp 12 months ago

update license

1
#2 opened 12 months ago by
mlabonne

add base_model

1
#1 opened 12 months ago by
mlabonne
New activity in argilla/distilabeled-OpenHermes-2.5-Mistral-7B 12 months ago

Can some one link me to gguf?

1
#1 opened 12 months ago by
Hugs4Llamas