Marc Kovka's picture

Marc Kovka

GPT007

·

AI & ML interests

None yet

Recent Activity

liked a model 7 days ago

gokaygokay/Flux-Watercolor-Strokes-LoRA

reacted to lewtun's post with 🔥 7 days ago

We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥 How? By combining step-wise reward models with tree search algorithms :) We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think" We're open sourcing the full recipe and sharing a detailed blog post. In our blog post we cover: 📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time. 🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets. 🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM Here's the links: - Blog post: https://huggingface.co/spaces/HuggingFaceH4/blogpost-scaling-test-time-compute - Code: https://github.com/huggingface/search-and-learn Enjoy!

View all activity

Organizations

None yet

GPT007's activity

New activity in google/gemma-2-9b 5 months ago

Gemma 2's Flash attention 2 implementation is strange...

#23 opened 6 months ago by

New activity in OpenCo7/UpVoteWeb 5 months ago

Best way to pull the data

#5 opened 5 months ago by

New activity in google/gemma-2-9b 5 months ago

Model repeating information and "spitting out" random characters

#14 opened 6 months ago by

New activity in Qwen/Qwen2-0.5B 5 months ago

Remove chat template

#2 opened 5 months ago by

New activity in HuggingFaceTB/SmolLM-360M 5 months ago

Remove chat template on base model (apply to other models too)

#4 opened 5 months ago by

Something is wrong?

#3 opened 5 months ago by

New activity in Xenova/experimental-phi3-webgpu 5 months ago

Firefox

#1 opened 8 months ago by

New activity in m3hrdadfi/typo-detector-distilbert-en 5 months ago

Update README.md

#2 opened 5 months ago by

New activity in microsoft/MInference 5 months ago

Why is it always saying "assistant" and "USER: "?

#2 opened 6 months ago by

New activity in google/gemma-2-9b-it 6 months ago

Flash attention 2 is not working

#9 opened 6 months ago by

New activity in google/gemma-2-9b 6 months ago

Inference error

#20 opened 6 months ago by

Error

#25 opened 6 months ago by

Gemma 2's Flash attention 2 implementation is strange...

#23 opened 6 months ago by

Gemma 2's Flash attention 2 implementation is strange...

#23 opened 6 months ago by