Files
reka-flash-3-GGUF/README.md

67 lines
2.8 KiB
Markdown
Raw Normal View History

---
base_model: RekaAI/reka-flash-3
pipeline_tag: text-generation
inference: true
language:
- en
license: apache-2.0
model_creator: RekaAI
model_name: reka-flash-3
model_type: llama
quantized_by: brittlewis12
tags:
- reasoning
- llama
---
# Reka Flash 3 (21B) GGUF
**Original model**: [Reka Flash 3](https://huggingface.co/RekaAI/reka-flash-3)
**Model creator**: [RekaAI](https://huggingface.co/RekaAI)
> Reka Flash 3 is a 21B general-purpose reasoning model that was trained from scratch. It was trained in synthetic and public datasets for supervised finetuning, followed by RLOO with model-based and rule-based rewards. It performs competitively with proprietary models such as OpenAI o1-mini, making it a good foundation to build applications that require low latency or on-device deployment.
This repo contains GGUF format model files for RekaAI’s Reka Flash 3.
### 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 b4872 (revision [ba76543](https://github.com/ggml-org/llama.cpp/commits/ba7654380a3c7c1b5ae154bea19134a3a9417a1e)),
using [autogguf-rs](https://github.com/brittlewis12/autogguf-rs).
### Prompt template: [Reka 3 Chat](https://huggingface.co/RekaAI/reka-flash-3/blob/5ebbf19d65a3d4e41c6dcb87cf61bcfbf0d08e0f/tokenizer_config.json#L197)
```
human: {{system_message}} {{prompt}} <sep> assistant:
```
---
## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!
![cnvrs.ai](https://pbs.twimg.com/profile_images/1744049151241797632/0mIP-P9e_400x400.jpg)
[cnvrs](https://testflight.apple.com/join/sFWReS7K) 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](https://huggingface.co/models?library=gguf)!
* 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](https://github.com/ggml-org/llama.cpp), with **haptics** during response streaming!
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!
* if you **already have the app**, download Reka Flash 3 now!
* <cnvrsai:///models/search/hf?id=brittlewis12/reka-flash-3-GGUF>
- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date
### Reka Flash 3 in cnvrs on macOS
![reka-flash-3 in cnvrs](https://cdn-uploads.huggingface.co/production/uploads/63b64d7a889aa6707f155cdb/T3sPfI1FBNggCFvIIpbsE.png)
---
## Original Model Evaluation
![reka-evals](https://huggingface.co/RekaAI/reka-flash-3/resolve/main/eval.png)