Qwen3 small models fine-tuned/merged on different datasets
AI & ML interests
None defined yet.
Recent Activity
Papers
REAM: Merging Improves Pruning of Experts in LLMs
Less is More: Recursive Reasoning with Tiny Networks
Compressed MoE models with a reduced number of experts. See additional models at https://huggingface.co/bknyaz.
-
SamsungSAILMontreal/Qwen3-235B-A22B-Instruct-2507-REAP
Text Generation • 178B • Updated • 19 • 1 -
SamsungSAILMontreal/Qwen3-30B-A3B-Instruct-2507-REAM
Text Generation • 23B • Updated • 254 • 7 -
bknyaz/Qwen3-Next-80B-A3B-Instruct-REAM
Text Generation • 60B • Updated • 472 • 5 -
bknyaz/Qwen3-235B-A22B-Instruct-2507-REAM
Text Generation • 178B • Updated • 7 • 1
Qwen3 small models fine-tuned/merged on different datasets
Compressed MoE models with a reduced number of experts. See additional models at https://huggingface.co/bknyaz.
-
SamsungSAILMontreal/Qwen3-235B-A22B-Instruct-2507-REAP
Text Generation • 178B • Updated • 19 • 1 -
SamsungSAILMontreal/Qwen3-30B-A3B-Instruct-2507-REAM
Text Generation • 23B • Updated • 254 • 7 -
bknyaz/Qwen3-Next-80B-A3B-Instruct-REAM
Text Generation • 60B • Updated • 472 • 5 -
bknyaz/Qwen3-235B-A22B-Instruct-2507-REAM
Text Generation • 178B • Updated • 7 • 1