Improve model card: Add Tequila paper, code link, and metadata
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -3,8 +3,19 @@ tags:
|
|
| 3 |
- hunyuan
|
| 4 |
- eagle3
|
| 5 |
- eagle
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
<p align="center">
|
| 9 |
<picture>
|
| 10 |
<source media="(prefers-color-scheme: dark)" srcset="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/logos/angelslim_logo_light.png?raw=true">
|
|
@@ -74,8 +85,10 @@ The Eagle3 weights for the Qwen3 series model are now available.
|
|
| 74 |
| Qwen3 Models | Hunyuan Models |
|
| 75 |
| ----------|----------|
|
| 76 |
| β
[Qwen3-1.7B](https://huggingface.co/AngelSlim/Qwen3-1.7B_eagle3) |β
[Hunyuan-1.8B-Instruct](https://huggingface.co/AngelSlim/Hunyuan-1.8B-Instruct_eagle3) |
|
| 77 |
-
| β
[Qwen3-4B](https://huggingface.co/AngelSlim/Qwen3-4B_eagle3)
|
| 78 |
-
|
|
|
|
|
|
|
| 79 |
| β
[Qwen3-14B](https://huggingface.co/AngelSlim/Qwen3-14B_eagle3) |
|
| 80 |
| β
[Qwen3-32B](https://huggingface.co/AngelSlim/Qwen3-32B_eagle3) |
|
| 81 |
| β
[Qwen3-30B-A3B](https://huggingface.co/AngelSlim/Qwen3-a3B_eagle3) |
|
|
@@ -351,7 +364,7 @@ The code for this project is open-sourced under the [License for AngelSlim](LICE
|
|
| 351 |
title={{AngelSlim}},
|
| 352 |
author={Tencent AngelSlim Project Contributors},
|
| 353 |
year={2025},
|
| 354 |
-
month={
|
| 355 |
url={https://github.com/Tencent/AngelSlim},
|
| 356 |
}
|
| 357 |
```
|
|
|
|
| 3 |
- hunyuan
|
| 4 |
- eagle3
|
| 5 |
- eagle
|
| 6 |
+
- tequila
|
| 7 |
+
- quantization
|
| 8 |
+
- ternary-quantization
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
library_name: transformers
|
| 11 |
+
license: apache-2.0
|
| 12 |
---
|
| 13 |
|
| 14 |
+
This repository is part of the **AngelSlim** project, a comprehensive LLMs compression toolkit that includes the **Tequila** quantization method.
|
| 15 |
+
|
| 16 |
+
The Tequila method was presented in the paper [Tequila: Trapping-free Ternary Quantization for Large Language Models](https://huggingface.co/papers/2509.23809).
|
| 17 |
+
The code for Tequila can be found at: https://github.com/Tencent/AngelSlim/tree/tequila/TernaryQuant
|
| 18 |
+
|
| 19 |
<p align="center">
|
| 20 |
<picture>
|
| 21 |
<source media="(prefers-color-scheme: dark)" srcset="https://github.com/Tencent/AngelSlim/blob/main/docs/source/assets/logos/angelslim_logo_light.png?raw=true">
|
|
|
|
| 85 |
| Qwen3 Models | Hunyuan Models |
|
| 86 |
| ----------|----------|
|
| 87 |
| β
[Qwen3-1.7B](https://huggingface.co/AngelSlim/Qwen3-1.7B_eagle3) |β
[Hunyuan-1.8B-Instruct](https://huggingface.co/AngelSlim/Hunyuan-1.8B-Instruct_eagle3) |
|
| 88 |
+
| β
[Qwen3-4B](https://huggingface.co/AngelSlim/Qwen3-4B_eagle3) |
|
| 89 |
+
β
[Hunyuan-4B-Instruct](https://huggingface.co/AngelSlim/Hunyuan-4B-Instruct_eagle3) |
|
| 90 |
+
| β
[Qwen3-8B](https://huggingface.co/AngelSlim/Qwen3-8B_eagle3) |
|
| 91 |
+
β
[Hunyuan-7B-Instruct](https://huggingface.co/AngelSlim/Hunyuan-7B-Instruct_eagle3) |
|
| 92 |
| β
[Qwen3-14B](https://huggingface.co/AngelSlim/Qwen3-14B_eagle3) |
|
| 93 |
| β
[Qwen3-32B](https://huggingface.co/AngelSlim/Qwen3-32B_eagle3) |
|
| 94 |
| β
[Qwen3-30B-A3B](https://huggingface.co/AngelSlim/Qwen3-a3B_eagle3) |
|
|
|
|
| 364 |
title={{AngelSlim}},
|
| 365 |
author={Tencent AngelSlim Project Contributors},
|
| 366 |
year={2025},
|
| 367 |
+
month={7},
|
| 368 |
url={https://github.com/Tencent/AngelSlim},
|
| 369 |
}
|
| 370 |
```
|