🔄 In a Training Loop

Syed Sarim Ahsan

sarimahsan101

2 2

·

AI & ML interests

LLM Fine-Tuning (LoRA, QLoRA), Multilingual Reasoning Models, Efficient Inference (4-bit/8-bit Quantization), NLP, Applied Machine Learning, AI System Design, Retrieval-Augmented Generation (RAG)

Recent Activity

updated a model 13 days ago

sarimahsan101/qwen2.5-3b-grpo-gsm8k

published a model 13 days ago

sarimahsan101/qwen2.5-3b-grpo-gsm8k

updated a model 16 days ago

sarimahsan101/Nova-MoE-122M

View all activity

Organizations

sarimahsan101 's models 20

sarimahsan101/qwen2.5-3b-grpo-gsm8k

Reinforcement Learning • 3B • Updated 13 days ago

sarimahsan101/Nova-MoE-122M

Text Generation • Updated 15 days ago • 10

sarimahsan101/Qwen2.5-0.5B-DPO-detox

0.5B • Updated 20 days ago • 24

sarimahsan101/gpt2-dpo-detox

Text Generation • 0.1B • Updated 21 days ago • 50

sarimahsan101/nova-141m-tinystories

Text Generation • 0.1B • Updated 23 days ago • 33

sarimahsan101/qwen2.5-0.5b-detox-ppo

Text Generation • 0.5B • Updated 30 days ago • 185

sarimahsan101/ppo-gpt2-imdb

Text Generation • 0.1B • Updated Jul 10 • 360

sarimahsan101/Qwen2.5-0.5B-HiddenDistilled-LoRA

Text Generation • Updated Jul 4 • 1

sarimahsan101/Qwen2.5-0.5B-HiddenDistilled

Text Generation • 0.5B • Updated Jul 4 • 66

sarimahsan101/hidden_distill_output

sarimahsan101/qwen2.5-7b-hallucination-probe

sarimahsan101/mini-qwen

Text Generation • 56.1M • Updated Jun 5 • 5

sarimahsan101/qwen2.5-3b-cot-gsm8k

sarimahsan101/os-network-intrusion-detector-bilstm

sarimahsan101/mistral-7b-ai-project-scoper-lora

Text Generation • Updated Apr 20 • 3

sarimahsan101/TinyLlama-1.1B-Alpaca-QLoRA

Text Generation • 1B • Updated Apr 19

sarimahsan101/qwen2.5-7b-thinking-esp

Text Generation • 8B • Updated Apr 19 • 10

sarimahsan101/opt-125m-alpaca-qlora

Text Generation • 0.2B • Updated Apr 19

sarimahsan101/medical_symptom_transformer

0.1B • Updated Jan 7 • 3

sarimahsan101/xray_disease_cnn_model