Llama3 8B LLM SFT+DPO and quantized LLM. Finetuned on EPFL tech courses and more (stack overflow books ...).
Peter A. Massih PRO
PeterAM4
AI & ML interests
LLMs, RL, Regressions, Diffusion
Recent Activity
updated a dataset about 6 hours ago
PeterAM4/priviledge-prospectus-rag-benchmark published a dataset about 6 hours ago
PeterAM4/priviledge-prospectus-rag-benchmark liked a model about 1 month ago
PeterAM4/Qwen3-Embedding-0.6B-GGUFOrganizations
models 10
PeterAM4/Qwen3-Embedding-0.6B-GGUF
Sentence Similarity • 0.6B • Updated • 1.92k • 1
PeterAM4/deepseek-paraphrase
Text Generation • 8B • Updated • 2 • 2
PeterAM4/gemma-2-2B-it-thinking-function_calling-test
Updated
PeterAM4/EPFL-TA-Meister-GPTQ-4bit
Text Generation • 8B • Updated • 5
PeterAM4/EPFL-TA-Meister-AWQ-4bit
Text Generation • 8B • Updated
PeterAM4/EPFL-TA-Meister-4bit
Text Generation • 8B • Updated • 2
PeterAM4/EPFL-TA-Meister-8bit
Text Generation • 8B • Updated • 3
PeterAM4/EPFL-TA-Meister
Text Generation • 8B • Updated • 3 • 3
PeterAM4/EPFL-TA-MeisterDPOv1
Text Generation • 8B • Updated • 4
PeterAM4/EPFL-TA-Meister-SFT
Text Generation • 8B • Updated • 2