Carlos Fonseca's picture

1 60

Carlos Fonseca

carlfm01

·

carlfm01

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

HuggingFaceTB/SmolLM2-360M

reacted to Jaward's post with 👀 4 days ago

Finally here it is: a faster, custom, scalable GRPO trainer for smaller models with < 500M params, can train on 8gb ram cpu, also supports gpu for sanity sake (includes support for vllm + flash attention). Using smolLM2-135M/360M-instructs as ref & base models. Experience your own “aha” moment 🐳 on 8gb ram. Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb

reacted to Jaward's post with 🔥 4 days ago

Finally here it is: a faster, custom, scalable GRPO trainer for smaller models with < 500M params, can train on 8gb ram cpu, also supports gpu for sanity sake (includes support for vllm + flash attention). Using smolLM2-135M/360M-instructs as ref & base models. Experience your own “aha” moment 🐳 on 8gb ram. Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb

View all activity

Organizations

None yet

models

None public yet

datasets

None public yet