Beketaut's picture

Beketaut

Kevusp187

·

AI & ML interests

Recent Activity

liked a Space 12 days ago

gradio/hello_world_4

reacted to sergiopaniego's post with 👍 12 days ago

Gemma 4 💎 is here and it’s strong! to celebrate, we’re rolling out in TRL: > support for multimodal tool responses for environments (OpenEnv) > an example to train it in CARLA for autonomous driving with image-based tool calls go check it out 🏎️🏎️ blog: https://huggingface.co/blog/gemma4 script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/carla_vlm_gemma.py

reacted to danielhanchen's post with 🔥 12 days ago

Google releases Gemma 4. ✨ Gemma 4 introduces 4 models: E2B, E4B, 26B-A4B, 31B. The multimodal reasoning models are under Apache 2.0. Run E2B and E4B on ~6GB RAM, and on phones. Run 26B-A4B and 31B on ~18GB. GGUFs: https://huggingface.co/collections/unsloth/gemma-4 Guide: https://unsloth.ai/docs/models/gemma-4

View all activity

Organizations

upvoted 20 collections 12 days ago

SAM3

6 items • Updated 19 days ago • 225

Trinity-Large-Thinking

5 items • Updated 5 days ago • 28

Meta's Llama 3.2 language models & evals

14 items • Updated Dec 13, 2024 • 413

NVIDIA Nemotron v3

Open, Production-ready Enterprise Models • 15 items • Updated 8 days ago • 267

LeWM

Official checkpoints and datasets related to LeWM paper. • 9 items • Updated 18 days ago • 23

Transformers.js V4 demos

A collection of demos built with Transformers.js V4 • 23 items • Updated 6 days ago • 50

Qwen-3.5-unsloth-mlx

AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 20 items • Updated 16 days ago • 20

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 2 days ago • 132

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated Mar 10 • 590

Unsloth Dynamic 2.0 Quants

New 2.0 version of our Dynamic GGUF + Quants. Dynamic 2.0 achieves superior accuracy & SOTA quantization performance. • 85 items • Updated 3 days ago • 524

200+ Roleplay, Creative Writing, Uncensored, NSFW models.

Oldest models listed first, with Newest models at bottom of the page. Most repos have full examples, instructions, best settings and so on. • 279 items • Updated 4 days ago • 655

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled-v2

15 items • Updated 5 days ago • 95

Qwopus3.5-v3

🌟Qwopus3.5-v3 is the latest model in the Claude series. • 12 items • Updated 5 days ago • 80

Raon

8 items • Updated 13 days ago • 45

Holo3

1 item • Updated 14 days ago • 34

Qwen3.5-Claude-4.6-Opus-Reasoning-Distilled

18 items • Updated 5 days ago • 199

UnifoLM_WBT_Dataset

8 items • Updated 18 days ago • 83

Qwen3.5

21 items • Updated Mar 9 • 1.51k

Bonsai

1-bit Bonsai models • 6 items • Updated about 19 hours ago • 171

Gemma 4

8 items • Updated 12 days ago • 600