John's picture

4

John

tachyon-beep

·

https://github.com/tachyon-beep/

tachyton-beep

AI & ML interests

Deep Reinforcement Learning Emergent Behaviour from Complex LLM Orchestration Emergent Cooperation in multi-agent Deep Reinforcement Learning.

Recent Activity

liked a model about 19 hours ago

mradermacher/L3.3-Damascus-R1-i1-GGUF

reacted to grimjim's post with 👀 5 months ago

I found this paper to be thought-provoking: "Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling" by Bansal, Hosseini, Agarwal, Tran, and Kazemi. https://arxiv.org/abs/2408.16737 The direct implication is that smaller models could be used to create cost-effective synthetic datasets. And on that note, in the Gemma terms of use, Google explicitly claims no rights on outputs generated from those models, which means one is free to synthgen from the Gemma line. Meta's Llama 3 licence forbids synthetic generation of outputs if used to improve other models. Relevant Mistral, Qwen, and Yi models under the Apache 2.0 license are unrestricted for this purpose.

liked a model 6 months ago

anthracite-org/magnum-v3-34b

View all activity

Organizations

None yet

models

None public yet

datasets

None public yet