Jordi

jordivcb's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset about 2 hours ago

nvidia/OpenCodeReasoning

Viewer • Updated 3 days ago • 585k • 2.65k • 137

upvoted a collection about 2 hours ago

Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 8 items • Updated 7 days ago • 111

liked a dataset 9 days ago

open-r1/codeforces-cots

Viewer • Updated 13 days ago • 254k • 12.7k • 132

liked a Space 15 days ago

Build error

251

251

Qwen2.5 Omni 7B Demo

🏆

Submit media inputs to generate text and speech responses

liked a dataset 17 days ago

glaiveai/reasoning-v1-20m

Viewer • Updated 22 days ago • 22.2M • 12.1k • 184

liked a model 17 days ago

mlabonne/gemma-3-4b-it-abliterated

Image-Text-to-Text • Updated 20 days ago • 2.74k • 17

liked a model 18 days ago

huihui-ai/gemma-3-4b-it-abliterated

Image-Text-to-Text • Updated 10 days ago • 457 • 9

New activity in kyutai/moshika-vis-pytorch-bf16 18 days ago

fix: changed to the correct project page link

2

#2 opened 20 days ago by

jordivcb

upvoted a collection 20 days ago

MoshiVis v0.1

Collection

MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 8 items • Updated 20 days ago • 22

reacted to mlabonne's post with 🔥👍 22 days ago

view post

Post

8095

✂️ AutoAbliteration

I made a Colab notebook to automatically abliterate models.

It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.

💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing

See translation

• 

👍

30

30

🔥

15

15

😎

5

5

❤️

4

4

🚀

2

2

+

Reply

upvoted a collection 29 days ago

Gemma 3 Release

Collection

17 items • Updated 7 days ago • 321

upvoted 2 collections about 1 month ago

Reasoning Datasets

Collection

Distilled synthetic Reasoning datasets • 7 items • Updated Feb 2 • 60

Instruct Models - Better instruction following.

Collection

Q6s Instruct models. Other Qs in model listing. Instruct models are better at one shot / api type usage in most cases vs "chat". See org model card. • 87 items • Updated 10 days ago • 5

liked a dataset about 1 month ago

HuggingFaceH4/grok-conversation-harmless

Viewer • Updated Feb 2, 2024 • 44.8k • 226 • 25

liked 3 models about 1 month ago

lmstudio-community/granite-vision-3.2-2b-GGUF

Image-Text-to-Text • Updated Feb 26 • 3.72k • 5

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • Updated 2 days ago • 956k • 1.28k

ibm-granite/granite-vision-3.1-2b-preview

Image-Text-to-Text • Updated Feb 26 • 4.67k • 95

liked a model about 2 months ago

perplexity-ai/r1-1776

Text Generation • Updated Feb 26 • 31.4k • • 2.22k

liked a dataset about 2 months ago

cognitivecomputations/dolphin-r1

Viewer • Updated Jan 30 • 814k • 1.91k • 277