---
language:
- en
tags:
- text-generation-inference
- text-generation
---

<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/Usz0Okcz85HrkdGLpMLKu.png" style="height: 400px;">

# Synth 2.5 Flash Preview


> [!Note]
> This is a preview model, it may deliver performance below that of the final model.<br>
> This preview is a model finetuned with purely **SFT**, RLAIF has **not** been applied yet.<br>
> Alongside this, creative performance is currently best on **non-thinking mode** for this preview.<br> 

Synth 2.5 is the next model in the Synth line-up, based on Ling 3 Tiny, it has 8B total parameters and 1B active parameters.

### Compared to Synth 2
Compared to Synth 2, 2.5 has the following changes/improvements:

- Trained on real-world creative data/usage from SOTA models (and past-sota, user-perferred models)

- Optimized for following user-wanted qualities (described [here](https://lucidity.sh/research/creative.html)) via RLAIF (READ NOTE FOR PREVIEW)

- Hybrid reasoning support, for optional further in-depth creative reasoning

### Usage

#### Composite and LuciditySH Platform

You can test Synth 2.5 Flash at [Composite](https://composite.lucidity.sh/) (creative specific) or LuciditySH Platform (coming soon) for free, with up to 100 free requests a day for easy testing/usage.

#### Local

You can use Synth 2.5 Flash on Llama.cpp ([1.0.10481](https://github.com/Start9Labs/llama-cpp-startos/pull/25)) or VLLM ([InclusionAI's Ling 3 fork](https://github.com/inclusionAI/vllm-ling-v3)) 

#### Generation Parameters

It is recommended to use Synth 2.5 Flash with the following generation settings:

- Temperature: 0.8-1
- Top-P: 0.95
- Top-K: 0

### Training

For the SFT stage of Synth 2.5's training, it was trained on a closed dataset comprised of real-world creative interactions with the following models, with the amount of interactions:

| Family | Samples |
|---|---:|
| Gemini (2.5 Pro) | 1 |
| Gemini (3.X Pro/3.7) | 1 |
| DeepSeek (V3 0324) | 5 |
| DeepSeek (R1 0528) | 8 |
| DeepSeek (V4 Pro) | 804 |
| GLM (5.X) | 1981 |
| GLM (4.X) | 58 |
| Kimi (k2.X) | 284 |
| Kimi (k3) | 3 |
| Minimax M3 | 69 |
| StepFun | 40 |
| **total** | **3254** |


<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/OMfjLL7rzSJQKOZIVL6PR.png" style="height: 350px;">

For model replication, close data to our closed dataset can be found in our [PIPKIN datasets](https://huggingface.co/datasets/LucidityAI/PIPKIN-Creative-174k).

### Limitations (for Preview)

As per the active parameter count of this model (1B) and the fact that it is only in preview, it comes with the following limitations, as flagged by Composite users:

- Synth 2.5 Flash Preview is incapable of following deep prompts that require heavy, specific formatting

- Synth 2.5 Flash Preview has been noted by users to occasionally write for them, a disruptive quality

### Considerations

Synth 2.5 Flash is capable of generating content that is harmful, illegal and/or generally NSFW, as with any LLM. It is recommended to put Synth 2.5 behind a moderation model or other safety layer for real world deployment.