68 lines
2.7 KiB
Markdown
68 lines
2.7 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
library_name: transformers
|
||
|
|
datasets:
|
||
|
|
- SL-AI/GRaPE-Base-Mix
|
||
|
|
base_model:
|
||
|
|
- LiquidAI/LFM2-700M
|
||
|
|
---
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
_The **G**eneral **R**easoning **A**gent (for) **P**roject **E**xploration_
|
||
|
|
|
||
|
|
# The GRaPE Family
|
||
|
|
| Attribute | Size | Modalities | Domain |
|
||
|
|
| :--- | :--- | :--- | :--- |
|
||
|
|
| **GRaPE Flash** | 7B A1B | Text in, Text out | High-Speed Applications |
|
||
|
|
| **GRaPE Mini** | 3B | Text + Image + Video in, Text out | On-Device Deployment |
|
||
|
|
| **GRaPE Nano** | 700M | Text in, Text out | Extreme Edge Deployment |
|
||
|
|
|
||
|
|
***
|
||
|
|
|
||
|
|
# Capabilities
|
||
|
|
|
||
|
|
The GRaPE Family was trained on about **14 billion** tokens of data after pre-training. About half was code related tasks, with the rest being heavy on STEAM. Ensuring the model has a sound logical basis.
|
||
|
|
> *GRaPE Nano does not have thinking capabilities, primarily in favor of instant responses.*
|
||
|
|
***
|
||
|
|
|
||
|
|
GRaPE Flash and Nano are monomodal models, only accepting text. GRaPE Mini being trained most recently supports image and video inputs.
|
||
|
|
|
||
|
|
# How to Run
|
||
|
|
|
||
|
|
I recommend using **LM Studio** for running GRaPE Models, and have generally found these sampling parameters to work best:
|
||
|
|
|
||
|
|
| Name | Value |
|
||
|
|
| :--- | :--- |
|
||
|
|
| **Temperature** | 0.6 |
|
||
|
|
| **Top K Sampling** | 40 |
|
||
|
|
| **Repeat Penalty** | 1 |
|
||
|
|
| **Top P Sampling** | 0.85 |
|
||
|
|
| **Min P Sampling** | 0.05 |
|
||
|
|
|
||
|
|
# GRaPE Nano as a Model
|
||
|
|
|
||
|
|
Recently there has been a push for smaller and smaller models. GRaPE Nano explores this by performing **full finetuning** on a 700M model, adapting it to the GRaPE style of outputs. Like GRaPE Flash, GRaPE Nano **does not** have thinking capabilities. Edge devices are often slow, and it would be worse to make it even slower.
|
||
|
|
|
||
|
|
# Architecture
|
||
|
|
|
||
|
|
* GRaPE Flash: Built on the `OlMoE` Architecture, allowing for incredibly fast speeds where it matters. Allows for retaining factual information, but lacks in logical tasks.
|
||
|
|
|
||
|
|
* GRaPE Mini: Built on the `Qwen3 VL` Architecture, allowing for edge case deployments, where logic cannot be sacrificed.
|
||
|
|
|
||
|
|
* GRaPE Nano: Built on the `LFM 2` Architecture, allowing for the fastest speed, and the most knowledge in the tiniest package.
|
||
|
|
|
||
|
|
***
|
||
|
|
|
||
|
|
# Notes
|
||
|
|
|
||
|
|
The GRaPE Family started all the way back in August of 2025, meaning these models are severely out of date on architecture, and training data.
|
||
|
|
|
||
|
|
GRaPE 2 will come sooner than the GRaPE 1 family had, and will show multiple improvements.
|
||
|
|
|
||
|
|
There are no benchmarks for GRaPE 1 Models due to the costly nature of running them, as well as prioritization of newer models.
|
||
|
|
|
||
|
|
Updates for GRaPE 2 models will be posted here on Huggingface, as well as [Skinnertopia](https://www.skinnertopia.com/)
|