🔄 In a Training Loop

Mohammad Bagher Bidram

Bidram

3 7 50

MB-Bidram

AI & ML interests

Programming, Computer, Math (A bit), SLMs (especially ones I can run on my GPU)

Recent Activity

upvoted an article 3 days ago

Harness adapters: Safe RL for efficient agentic development

new activity 3 days ago

ccore/Qwen3.5-4B-3D-Coder:Model's quality

liked a model 4 days ago

peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP

View all activity

Organizations

None yet

upvoted an article 3 days ago

Article

Harness adapters: Safe RL for efficient agentic development

harness-hub

•

4 days ago

• 45

New activity in ccore/Qwen3.5-4B-3D-Coder 3 days ago

Model's quality

❤️ 1

#19 opened 3 days ago by

Bidram

liked a model 4 days ago

peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP

Image-Text-to-Text • 36B • Updated 15 days ago • 992k • 368

New activity in huggingface/InferenceSupport 5 days ago

cybertruck32489/LFM3-1.7B-RD

➕ 1

#13416 opened 5 days ago by

Bidram

liked 2 models 5 days ago

cybertruck32489/LFM3-1.7B-RD

Text Generation • 2B • Updated 9 days ago • 3.55k • 3

Shivansh-13929/LFM3-2.2B-Omni-Coder-Instruct

Text Generation • 2B • Updated 6 days ago • 121 • 3

reacted to sergiopaniego's post with 👍🔥 5 days ago

Post

4,629

TRL now supports MOPD (Multi-Teacher On-Policy Distillation) natively❗️

Many frontier open models use it. labs train one RL expert per domain and then distill them all into one model

Blog with what it is, who uses it and an experiment you can run on HF Jobs with one command

https://huggingface.co/blog/sergiopaniego/mopd-trl