Kevin Wu

Flagpoles00's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 24 days ago

zed-industries/zeta

Updated 14 days ago • 2.4k • 228

liked a Space 24 days ago

Running

71

71

Graphic Novel- NSFW Adult

🖊

Create stunning graphic novels effortlessly with AI

liked a model 24 days ago

AlejandroOlmedo/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-8bit-mlx

Text Generation • Updated 18 days ago • 200 • 3

reacted to Jaward's post with 👍 24 days ago

view post

Post

3867

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

See translation

• 

• 
• 
• 2 replies

·

👀

8

8

🔥

7

7

❤️

3

3

👍

2

2

🧠

2

2

+

Reply

liked 8 models 24 days ago

deepseek-ai/DeepSeek-V3

Text Generation • Updated 17 days ago • 3.12M • • 3.63k

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated Feb 1 • 264k • 3.21k

AlejandroOlmedo/DeepScaleR-1.5B-Preview-8bit-mlx

Text Generation • Updated 18 days ago • 190 • 2

AlejandroOlmedo/DeepScaleR-1.5B-Preview-mlx

Text Generation • Updated 18 days ago • 119 • 3

agentica-org/DeepScaleR-1.5B-Preview

Text Generation • Updated 18 days ago • 76.9k • • 520

unsloth/Qwen2.5-Math-7B

Text Generation • Updated Nov 12, 2024 • 3.49k • 3

Qwen/Qwen2.5-Math-7B

Text Generation • Updated Sep 23, 2024 • 252k • 72

Qwen/Qwen2.5-14B

Text Generation • Updated Sep 20, 2024 • 80.9k • 103