Mohammed karimi

Mohammedkarimi

4 1

AI & ML interests

None yet

Recent Activity

reacted to nwaughachukwuma's post with 🔥 about 13 hours ago

Following this post - https://huggingface.co/posts/nwaughachukwuma/366831808712777, I made another run on a fresh RTX PRO 4000 using inkling, gemini-3.5-flash, and glm-5.2+mm-ctx | case | gemini-3.5-flash @k=1 | glm-5.2+mm @k=1 | inkling @k=1 | | --- | --- | --- | --- | | **MEAN correctness** | **78.2** | **79.5** | **57.9** | | **MEAN speed (s)** | **111** | **123** | **69** | | **completed (case-runs)** | **20/23** | **21/23** | **18/23** |

new activity about 13 hours ago

BananaMind/BananaMind-2-Micro:Final Loss?

new activity 4 days ago

litert-community/MobileNet-v3-small:Replace the dynamic int8 file with a weight-only int8 file

View all activity

Organizations

None yet

reacted to nwaughachukwuma's post with 🔥 about 13 hours ago

Post

2022

Following this post - https://huggingface.co/posts/nwaughachukwuma/366831808712777, I made another run on a fresh RTX PRO 4000 using inkling, gemini-3.5-flash, and glm-5.2+mm-ctx

| case | gemini-3.5-flash @k=1 | glm-5.2+mm @k=1 | inkling @k=1 |
| --- | --- | --- | --- |
| **MEAN correctness** | **78.2** | **79.5** | **57.9** |
| **MEAN speed (s)** | **111** | **123** | **69** |
| **completed (case-runs)** | **20/23** | **21/23** | **18/23** |

New activity in BananaMind/BananaMind-2-Micro about 13 hours ago

Final Loss?

#2 opened about 24 hours ago by

Harley-ml

New activity in litert-community/MobileNet-v3-small 4 days ago

Replace the dynamic int8 file with a weight-only int8 file

#2 opened 5 days ago by

mlboydaisuke

replied to onekq's post 4 days ago

In the coming months I will introduce an open source, open weight model with eight processing layers. I hope to be able to release it soon.

New activity in litert-community/gemma-4-E2B-it-litert-lm 4 days ago

Please update chat_template.jinja to canonical Gemma 4 template (+ existing .litertlm files are now stale)

#43 opened 7 days ago by

deper

New activity in litert-community/Ministral-3-3B-Reasoning-2512 4 days ago

Hello :)

❤️ 1

#1 opened 4 days ago by

jegly

reacted to onekq's post with 🔥 4 days ago

Post

2650

Looking forward to the Qwen 3.8 model drop, and congratulations on joining the trillion parameters club.

But my eyes are on the promised 27B model. Small (<50B) models decline on OpenRouter, because they are being run on local devices. If people see the family trees here on HF they will understand.