base_model: arcee-ai/Arcee-Maestro-7B-Preview
pipeline_tag: text-generation
inference: true
language:
- en
license: apache-2.0
model_creator: arcee-ai
model_name: Arcee-Maestro-7B-Preview
model_type: qwen2
quantized_by: brittlewis12
tags:
- reasoning
- qwen2
Arcee Maestro 7B Preview GGUF
Original model: Arcee Maestro 7B Preview
Model creator: Arcee AI
Arcee-Maestro-7B-Preview (7B) is Arcee's first reasoning model trained with reinforment learning. It is based on the Qwen2.5-7B DeepSeek-R1 distillation DeepSeek-R1-Distill-Qwen-7B with further GRPO training. Though this is just a preview of our upcoming work, it already shows promising improvements to mathematical and coding abilities across a range of tasks.
Reinforcement Learning: GRPO with 450,000 verified math problems with some coding examples
This repo contains GGUF format model files for Arcee AI’s Arcee Maestro 7B Preview.
What is GGUF?
GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023.
Converted with llama.cpp build 4748 (revision c392e50), using autogguf-rs.
Prompt template: DeepSeek R1
{{system_message}}<｜User｜>{{prompt}}<｜Assistant｜><think>
Download & run with cnvrs on iPhone, iPad, and Mac!
cnvrs is the best app for private, local AI on your device:
- create & save Characters with custom system prompts & temperature settings
- download and experiment with any GGUF model you can find on HuggingFace!
- or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more!
- make it your own with custom Theme colors
- powered by Metal ⚡️ & Llama.cpp, with haptics during response streaming!
- try it out yourself today, on Testflight!
- if you already have the app, download Arcee Maestro 7B Preview now!
- cnvrsai:///models/search/hf?id=brittlewis12/Arcee-Maestro-7B-Preview-GGUF
- follow cnvrs on twitter to stay up to date
Original Model Evaluation
Arcee Maestro 7B preview shows great gains in mathematics and coding, surpassing O1 preview in many metrics.
