GGUF builds of MiniCPM5-2B-Math, a 2.5B math and proof specialist, for llama.cpp, Ollama and LM Studio. Pair it with the MiniCPM-Math Harness to run a small proof swarm on a laptop. Converted with llama.cpp b10964 (converthftogguf.py, tokenizer pre-type minicpm5) and quantized with llama-quantize`. The recommended sampling settings (temperature 0.9, top-p 0.95, min-p 0, top-k off) are embedded in the GGUF metadata, so llama.cpp uses them by default. All results on the model card were measured with the BF16 safetensors on vLLM. — —jinja uses the embedded chat template (thinking mode, … ). — -np 4 -kvu gives 4 parallel slots that share a 96K-token KV cache: one slot per agent for the harness. Run the harness with —profile quick against this server. — —port 8000 is where the harness looks by default; without it, llama-server listens on 8080. — The embedded defaults already set minp=0`; llama.cpp’s usual 0.05 can encourage repetition with this model. Start the server with a larger context window (for example OLLAMACONTEXTLENGTH=65536 ollama serve), because proofs routinely need tens of thousands of tokens. With the harness, pass —base-url http://127.0.0.1:11434/v1 —model…
Модальности:
Генерация текста
Области применения:
Математика Логика и рассуждение Диалог / чат
Задача: Генерация текста
Автор: Caldalis
Теги: gguf, minicpm, minicpm5, math, reasoning, theorem-proving, llama.cpp, en
Лайков: 3 | Загрузок: 9,623
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.