Mikhail
RefalMachine
AI & ML interests
NLP
Recent Activity
upvoted a paper about 1 month ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare upvoted a paper 3 months ago
Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM commentedon a paper 3 months ago
Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLMOrganizations
models 184
RefalMachine/RuadaptQwen3-4B-Hybrid-GGUF
4B • Updated • 331 • 2
RefalMachine/RuadaptQwen3-4B-Hybrid
4B • Updated • 474 • 3
RefalMachine/RuadaptQwen3-8B-Hybrid-GGUF
8B • Updated • 348 • 5
RefalMachine/RuadaptQwen3-8B-Hybrid
8B • Updated • 460 • 7
RefalMachine/RuadaptQwen3-4B-Instruct-GGUF
4B • Updated • 531 • 6
RefalMachine/RuadaptQwen3-4B-Instruct
4B • Updated • 1.8k • 10
RefalMachine/RuadaptQwen2.5-7B-Lite-Beta
Text Generation • 8B • Updated • 78 • 10
RefalMachine/RuadaptQwen2.5-1.5B-instruct
Text Generation • 2B • Updated • 90 • 8
RefalMachine/RuadaptQwen3-32B-Instruct-GGUF
33B • Updated • 304 • 13
RefalMachine/RuadaptQwen3-32B-Instruct
33B • Updated • 1.32k • 19
datasets 10
RefalMachine/ruadapt_hybrid_instruct
Viewer • Updated • 86.6k • 17
RefalMachine/ruadapt_instruct_2507
Viewer • Updated • 102k • 22
RefalMachine/llmtf_bench_data
Viewer • Updated • 14.2k • 459
RefalMachine/llmtf_open_benchmark
Updated • 310 • 2
RefalMachine/nerel-bio-simple
Viewer • Updated • 765 • 137
RefalMachine/darumeru
Viewer • Updated • 36.4k • 274 • 1
RefalMachine/hybrid_reasoning_dataset_ru
Viewer • Updated • 82.5k • 23 • 4
RefalMachine/GrandMaster-PRO-MAX-Qwen3-synthetic
Viewer • Updated • 49.7k • 19 • 3
RefalMachine/ruopinionne
Viewer • Updated • 4.68k • 111 • 2
RefalMachine/nerel_simple
Viewer • Updated • 9.55k • 25 • 1