‌ ​ ‍ ​ ‎ ‏ ‌ ​ ‍ ​

Maani's activity

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

liked a dataset about 17 hours ago

Glint-Research/Fable-5-traces

Updated 6 days ago • 23.2k • 392

New activity in google/gemma-4-E2B-it 5 days ago

Appreciation Post

❤️ 3

2

#37 opened 6 days ago by

Maani

upvoted a collection 5 days ago

Gemma 4

Collection

15 items • Updated 14 days ago • 987

liked 3 models 6 days ago

google/gemma-4-12B-it

Any-to-Any • 12B • Updated 20 days ago • 2.11M • 1.16k

google/gemma-4-E2B-it

Any-to-Any • 5B • Updated 21 days ago • 2.35M • 776

google/gemma-4-E4B-it

Any-to-Any • 8B • Updated 21 days ago • 6.13M • 1.28k

liked a model 20 days ago

LiquidAI/LFM2.5-8B-A1B

Text Generation • 8B • Updated 14 days ago • 199k • 636

New activity in allura-forge/Llama-3.3-8B-Instruct 5 months ago

This model is broken.

7

#4 opened 6 months ago by

Maani

liked 3 models 6 months ago

LiquidAI/LFM2.5-VL-1.6B

Image-Text-to-Text • 2B • Updated Mar 30 • 64k • 301

LiquidAI/LFM2.5-1.2B-Instruct-GGUF

Text Generation • 1B • Updated Apr 6 • 58.6k • 182

LiquidAI/LFM2.5-1.2B-Instruct

Text Generation • 1B • Updated 8 days ago • 120k • 617

New activity in EssentialAI/rnj-1-instruct 6 months ago

gemma3 is absolutely trash.

🤯 2

#9 opened 6 months ago by

Maani

liked 2 models 6 months ago

LiquidAI/LFM2-2.6B-Exp

Text Generation • 3B • Updated Mar 30 • 10.9k • 339

swiss-ai/Apertus-8B-Instruct-2509

Text Generation • 8B • Updated 4 days ago • 107k • • 470

upvoted a collection 6 months ago

Nemotron-Post-Training-v3

Collection

Collection of datasets used in the post-training phase of Nemotron Nano, Super, and Ultra v3. • 50 items • Updated 13 days ago • 166

liked a model 6 months ago

allenai/Bolmo-7B

Text Generation • 8B • Updated 7 days ago • 340 • 58

liked 2 models 7 months ago

ServiceNow-AI/Apriel-1.6-15b-Thinker

Image-Text-to-Text • 15B • Updated Dec 22, 2025 • 195 • 301

cyankiwi/rnj-1-instruct-AWQ-4bit

2B • Updated Dec 6, 2025 • 31 • 2

reacted to sergiopaniego's post with 🚀 7 months ago

view post

Post

3121

NEW: @EssentialAI just released Rnj-1, their first 8B model.

You can easily fine-tune it with GRPO using TRL to add reasoning capabilities to a compact mode

Free Colab link: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_rnj_1_instruct.ipynb

More free TRL notebooks: https://huggingface.co/docs/trl/main/en/example_overview#notebooks

See translation

• 

🚀

7

7

+

Reply

New activity in EssentialAI/rnj-1-instruct 7 months ago

After a long time, finally a capable little coder!

😎❤️ 4

7

#2 opened 7 months ago by

MrDevolver