ethicalabs/ouroboros
Viewer
•
Updated
•
625
•
108
Massimo Roberto Scamarcia
mrs83
·
AI & ML interests
Natural Language Processing, Text Generation, Question Answering, Data Augmentation, Knowledge Transfer, Chain-of-Thought
Recent Activity
updated
a dataset
about 5 hours ago
ethicalabs/ouroboros
updated
a collection
6 days ago
Ouroboros
published
a dataset
6 days ago
ethicalabs/ouroboros
Organizations
mrs83's activity
updated
a
dataset
about 5 hours ago
updated
a
collection
6 days ago
published
a
dataset
6 days ago
updated
a
model
9 days ago
reacted to
Jaward's
post with 🔥
9 days ago
Post
3826
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
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb
- 2 replies
liked
a
Space
9 days ago
updated
a
model
11 days ago
published
a
model
11 days ago
updated
a
model
11 days ago
published
a
model
11 days ago
liked
a
dataset
14 days ago
updated
a
model
16 days ago
updated
a
Space
17 days ago
updated
2
models
18 days ago
published
a
Space
18 days ago
updated
2
collections
18 days ago
updated
a
model
18 days ago