aquiffoo's picture

In a Training Loop 🔄

aquiffoo

aquiffoo

·

https://aquiffoo.is-a.dev/

AI & ML interests

thanks for everything.

Recent Activity

liked a model about 2 hours ago

NousResearch/NousCoder-14B

reacted to sergiopaniego's post with 🔥 about 2 hours ago

New GRPO + TRL free Colab notebook out! 🔥 Fine-tune 7B+ models on T4 GPUs thanks to a ton of memory optimizations for GRPO 7B model uses only 9.2 GB VRAM (~7× reduction) 🤯 Try the notebook here 👉 https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_trl_lora_qlora.ipynb

reacted to Reality123b's post with 🤗 about 23 hours ago

Happy birthday to me!!!

View all activity

Organizations

liked a model about 2 hours ago

NousResearch/NousCoder-14B

Text Generation • 15B • Updated 4 days ago • 186 • 70

reacted to sergiopaniego's post with 🔥 about 2 hours ago

Post

1221

New GRPO + TRL free Colab notebook out! 🔥

Fine-tune 7B+ models on T4 GPUs thanks to a ton of memory optimizations for GRPO

7B model uses only 9.2 GB VRAM (~7× reduction) 🤯

Try the notebook here 👉 https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_trl_lora_qlora.ipynb

reacted to Reality123b's post with 🤗 about 23 hours ago

Post

1497

Happy birthday to me!!!

1 reply

·

upvoted a collection 1 day ago

Jamba2

Jamba2 is a highly-efficient open source family of language models built for maximum reliability and steerability in the enterprise. • 3 items • Updated 1 day ago • 5

liked 2 models 1 day ago

ai21labs/AI21-Jamba2-3B

Text Generation • 3B • Updated about 9 hours ago • 78 • 23

ai21labs/AI21-Jamba2-Mini

Text Generation • 52B • Updated about 9 hours ago • 43 • 30

reacted to mlabonne's post with 🚀 1 day ago

Post

3507

New family of 1B models just dropped!

> LiquidAI/LFM2.5-1.2B-Base: 10T → 28T tokens
> LiquidAI/LFM2.5-1.2B-Instruct: new large-scale multi-stage RL
> LiquidAI/LFM2.5-1.2B-JP: our most polite model
> LiquidAI/LFM2.5-VL-1.6B: multi-image multilingual
> LiquidAI/LFM2.5-Audio-1.5B: 8x times faster, no quality loss

Super proud of this release 🤗

3 replies

·

liked 2 models 3 days ago

Lightricks/LTX-2

Image-to-Video • Updated 1 day ago • 330k • • 695

LiquidAI/LFM2.5-1.2B-Base

Text Generation • 1B • Updated 4 days ago • 273 • 53

upvoted a collection 3 days ago

💧 LFM2.5

Collection of Instruct, Base, and Japanese LFM2.5-1.2B models. • 19 items • Updated 4 days ago • 59

liked a model 3 days ago

LiquidAI/LFM2.5-1.2B-Instruct

Text Generation • 1B • Updated about 17 hours ago • 5.79k • 222

liked a model 4 days ago

miromind-ai/MiroThinker-v1.5-235B

Text Generation • 235B • Updated 3 days ago • 921 • 179

New activity in aquiffoo/neo-3-1B-A90M-Base 5 days ago

Production deployment considerations

#1 opened 6 days ago by

updated 2 models 8 days ago

aquiffoo/neo-3-3B-A400M-Base

Text Generation • 3B • Updated 8 days ago • 7 • 1

aquiffoo/neo-3-1B-A90M-Base

Text Generation • 1.0B • Updated 8 days ago • 18 • 1

updated a collection 9 days ago

neo-3

My series of fully open, state-of-the-art small mixture-of-experts models. • 11 items • Updated 9 days ago