CCR's picture

In a Training Loop 🔄

CCR

CCRss

·

AI & ML interests

- LLM and VLM training, - quantization, - faster inference, - synthetic data generation - ShowUI concept (computer use) - lora models for video generation

Recent Activity

published a model 1 day ago

CCRss/kz_stable

liked a Space about 1 month ago

sentence-transformers/quantized-retrieval

liked a model about 2 months ago

nvidia/NitroGen

View all activity

Organizations

published a model 1 day ago

CCRss/kz_stable

8B • Updated Sep 11, 2024 • 1

liked a Space about 1 month ago

Quantized Retrieval

Efficient quantized retrieval over Wikipedia

liked a model about 2 months ago

nvidia/NitroGen

Reinforcement Learning • Updated 12 days ago • 500

updated a dataset about 2 months ago

CCRss/ILSVRC_images_10_class

Viewer • Updated Dec 26, 2025 • 13k • 38

published a dataset about 2 months ago

CCRss/ILSVRC_images_10_class

Viewer • Updated Dec 26, 2025 • 13k • 38

upvoted a collection 2 months ago

T5Gemma 2

3 items • Updated Dec 18, 2025 • 66

liked a model 2 months ago

zai-org/AutoGLM-Phone-9B

Image-Text-to-Text • Updated Jan 7 • 13.9k • 422

upvoted a paper 2 months ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

Paper • 2512.10430 • Published Dec 11, 2025 • 115

liked a Space 3 months ago

Qwen-VL Object-Detection

Compare Qwen-VL models for object detection.

liked 2 models 3 months ago

eigen-ai-labs/eigen-banana-qwen-image-edit

Text-to-Image • Updated Nov 16, 2025 • 18 • 256

autoweeb/Qwen-Image-Edit-2509-Photo-to-Anime

Image-to-Image • Updated Nov 11, 2025 • 262k • • 115

published a model 3 months ago

CCRss/Qwen3-VL-4B-Instruct-trl-grpo

Updated Nov 5, 2025

New activity in maya-research/maya1 3 months ago

[ISSUE] Transformers inference script doesn't work.

#2 opened 3 months ago by

liked a model 3 months ago

maya-research/maya1

Text-to-Speech • Updated Nov 12, 2025 • 81.6k • 866

liked a Space 4 months ago

The Smol Training Playbook

The secrets to building world-class LLMs

upvoted a paper 4 months ago

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30, 2025 • 110

liked 4 models 4 months ago

BAAI/Emu3.5

Any-to-Any • 34B • Updated Dec 25, 2025 • 345 • 167

lightx2v/Autoencoders

Updated Nov 21, 2025 • 6.04k • 113

chestnutlzj/Edit-R1-Qwen-Image-Edit-2509

Image-to-Image • Updated Nov 4, 2025 • 193 • 45

Qwen/Qwen3-VL-30B-A3B-Instruct

Image-Text-to-Text • 31B • Updated Nov 26, 2025 • 1.5M • • 533