inspire's picture

In a Training Loop 🔄

inspire PRO

inspirebek

·

ubranch

AI & ML interests

CUDA out of memory.

Recent Activity

liked a model 3 days ago

nvidia/Nemotron-Cascade-2-30B-A3B

liked a model 6 days ago

Qwen/Qwen3-Reranker-4B

liked a Space 6 days ago

mteb/leaderboard

View all activity

Organizations

upvoted a collection 21 days ago

Uzbek TTS

1 item • Updated 23 days ago • 2

upvoted a collection 27 days ago

pplx-embed

Diffusion-Pretrained Dense and Contextual Embeddings • 7 items • Updated 28 days ago • 94

upvoted a collection 2 months ago

TranslateGemma

3 items • Updated 14 days ago • 223

upvoted a collection 5 months ago

Nanonets-OCR2

2 items • Updated Oct 13, 2025 • 25

upvoted 3 changelogs 7 months ago

Hugging Face Changelog

Introducing a better Hugging Face CLI

Jul 25, 2025

• 96

Hugging Face Changelog

Trending Papers

Jul 28, 2025

• 106

Hugging Face Changelog

Introducing HF Jobs: Run scalable compute jobs on Hugging Face

Jul 30, 2025

• 201

upvoted a paper 8 months ago

Efficient Agents: Building Effective Agents While Reducing Cost

Paper • 2508.02694 • Published Jul 24, 2025 • 86

upvoted a paper 11 months ago

Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG

Paper • 2410.05983 • Published Oct 8, 2024 • 2

upvoted a collection 11 months ago

Search-R1-v0.2

Exploration with a more stable RL pipeline with outcome-only reward and scaled-up LLMs. https://arxiv.org/abs/2503.09516 • 26 items • Updated Aug 12, 2025 • 5

upvoted 6 collections about 1 year ago

reranking series v2

V2 crispy rerank series • 3 items • Updated Jun 25, 2025 • 25

DeepSeek R1 (All Versions)

DeepSeek-R1-0528 is here! The most powerful reasoning open LLM, available in GGUF, original & 4-bit formats. Includes Llama & Qwen distilled models. • 37 items • Updated 14 days ago • 266

Cohere Labs Aya 23

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 3 items • Updated Jul 31, 2025 • 57

Cohere Labs Aya Expanse

Aya Expanse is an open-weight research release of a model with highly advanced multilingual capabilities. • 4 items • Updated Jul 31, 2025 • 43

Deepseek Papers

Deepseek papers collection • 31 items • Updated 10 days ago • 334

UzLLM

A collection of Uzbek-adapted LLMs. • 4 items • Updated Dec 4, 2024 • 6

upvoted a paper about 1 year ago

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

Paper • 2501.07888 • Published Jan 14, 2025 • 15

upvoted a collection about 1 year ago

InternLM3

6 items • Updated Dec 30, 2025 • 30

upvoted 2 collections over 1 year ago

DeepSeek-VL2

5 items • Updated Nov 27, 2025 • 80

LipSync and Face Operations

23 items • Updated 12 days ago • 63