maylore-ai/Temper-2-Ion-GGUF
Text Generation • 0.5B • Updated • 142 • 2
Maylore
community
AI & ML interests
Small language models, code generation, Rust, fine-tuning, reinforcement learning, benchmarks
Recent Activity
View all activity
Organization Card
Maylore
Maylore develops compact language models specialized in narrow tasks that run on most consumer PCs and laptops. The Temper models write Rust and run locally in LM Studio, Ollama or llama.cpp.
- Temper-2-Ion 0.5B model fine-tuned from Qwen2.5-Coder-0.5B-Instruct and trained with reinforcement learning. Understands requests in Russian and English and solves 32% more HumanEval-Rust tasks than Temper-1-0.5B.
- Temper-2-Ion-GGUF GGUF Q8_0 and BF16 for local use.
- Temper-1-1.5B fine-tuned from Qwen2.5-Coder-1.5B-Instruct on 10,000 Rust examples.
- Temper-1-1.5B-GGUF GGUF Q8_0 for local use.
- Temper-1-0.5B fine-tuned from Qwen2.5-Coder-0.5B-Instruct on 10,000 Rust examples and trained with reinforcement learning.
- Temper-1-0.5B-GGUF GGUF Q8_0 for local use.
Website: maylore.com
models 6
maylore-ai/Temper-2-Ion
Text Generation • 0.5B • Updated • 298
maylore-ai/Temper-1-1.5B-GGUF
Text Generation • 2B • Updated • 318 • 1
maylore-ai/Temper-1-1.5B
Text Generation • 2B • Updated • 1.2k • 3
maylore-ai/Temper-1-0.5B-GGUF
Text Generation • 0.5B • Updated • 312
maylore-ai/Temper-1-0.5B
Text Generation • 0.5B • Updated • 681 • 2
datasets 0
None public yet