Viewing profile — sumo43

Try running this using their harness https://huggingface.co/flashresearch/FlashResearch-4B-Thinki...

I made a 4B Qwen3 distill of this model (and a synthetic dataset created with it) a while back. Both can be found here: https://huggingface.co/flashresearch

I think the fine tuned policies are still very brittle, but I agree that this is super promising. It's also one of the most open (the model is still closed) research blogposts we'v…

seems like an improvement on the aloha approach? You still need to finetune it on roughly the same amount of OOD examples. Contrast this with google's approach over 2023, which was…

Location: US Remote: Yes Willing to relocate: Yes (US) Technologies: Python, PyTorch, HuggingFace, C++ Résumé/CV: https://drive.google.com/file/d/1qY-m1tKz4_QpHgxaGryC2vk-DGs... Em…

Maybe true for instruct, but pretraining datasets do not usually contain GPT-4 outputs. So the base model does not rely on GPT-4 in any way.

SEEKING VOLUNTEERS: open source self-play training for language models we are a small team associated with EleutherAI. looking to push the frontier of open source language models t…

For training you would need more memory. As for the pooling, Theoretically yes but wouldn't latency play as much, if not a greater part in the response time here? Imagine a tensor-…

Cool service. It's worth noting that, with quantization/QLORA, models as big as llama2-70b can be run on consumer hardware (2xRTX 3090) at acceptable speeds (~20t/s) using framewor…

Hello, I'm planning to participate in this challenge. I have experience training/prompting and building products from LLMs, I've also participated in a few CTFs. sumo43@proton.me