Djuunaa's picture

Djuunaa

djuna

·

AI & ML interests

None yet

Recent Activity

liked a model about 4 hours ago

Alibaba-NLP/gte-modernbert-base

reacted to hbseong's post with 👀 about 5 hours ago

🚨🔥 New Release Alert! 🔥🚨 Introducing the 435M model that outperforms Llama-Guard-3-8B while slashing 75% of the computation cost! 💻💥 👉 Check it out: https://huggingface.co/hbseong/HarmAug-Guard (Yes, INFERENCE CODE INCLUDED! 💡) More details in our paper: https://arxiv.org/abs/2410.01524 📜 #HarmAug #LLM # Safety #EfficiencyBoost #Research #AI #MachineLearning

reacted to lewtun's post with 🔥 about 5 hours ago

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! 🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. 🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code. 🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1

View all activity

Organizations

djuna's activity

upvoted a collection about 16 hours ago

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 2 items • Updated about 23 hours ago • 71

upvoted a collection 3 days ago

AI4Privacy_v2

Collection for AI4Privacy Version 2 trained on PII200k • 6 items • Updated Sep 25, 2024 • 4

upvoted a collection 4 days ago

DeepSeek R1 AWQ

7 items • Updated 5 days ago • 4

upvoted 2 papers 5 days ago

Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models

Paper • 2501.11873 • Published 6 days ago • 59

HALO: Hadamard-Assisted Lossless Optimization for Efficient Low-Precision LLM Training and Fine-Tuning

Paper • 2501.02625 • Published 22 days ago • 1

upvoted 2 collections 5 days ago

QTIP Quantized Models

See https://github.com/Cornell-RelaxML/qtip • 30 items • Updated Dec 9, 2024 • 11

Quantized DeepSeek R1 Distill

3 items • Updated 5 days ago • 3

upvoted 2 collections 21 days ago

Small Reasoning Model

7 items • Updated 7 days ago • 4

Dolphin 3.0

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. • 7 items • Updated 22 days ago • 58

upvoted a collection about 1 month ago

Falcon3

Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters. • 40 items • Updated 19 days ago • 81

upvoted an article 4 months ago

Article

Introducing Community Tools on HuggingChat

Sep 16, 2024

• 34

upvoted a collection 6 months ago

FP8 LLMs for vLLM

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17, 2024 • 62