munish0838
commited on
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: seallms
|
4 |
+
license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
tags:
|
7 |
+
- mistral
|
8 |
+
- multilingual
|
9 |
+
- sea
|
10 |
+
- conversational
|
11 |
+
base_model: SeaLLMs/SeaLLM-7B-v2
|
12 |
+
---
|
13 |
+
|
14 |
+
# SeaLLM-7B-v2-GGUF
|
15 |
+
- This is GGUF quantized evrsion of [SeaLLMs/SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2)
|
16 |
+
|
17 |
+
|
18 |
+
## Model Description
|
19 |
+
|
20 |
+
We introduce [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2), the state-of-the-art multilingual LLM for Southeast Asian (SEA) languages ๐ฌ๐ง ๐จ๐ณ ๐ป๐ณ ๐ฎ๐ฉ ๐น๐ญ ๐ฒ๐พ ๐ฐ๐ญ ๐ฑ๐ฆ ๐ฒ๐ฒ ๐ต๐ญ. It is the most significant upgrade since [SeaLLM-13B](https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat), with half the size, outperforming performance across diverse multilingual tasks, from world knowledge, math reasoning, instruction following, etc.
|
21 |
+
|
22 |
+
### Highlights
|
23 |
+
* [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) achieves the **7B-SOTA** on the **Zero-shot CoT GSM8K** task with **78.2** score and outperforms GPT-3.5 in many GSM8K-translated tasks in SEA languages (๐จ๐ณ ๐ป๐ณ ๐ฎ๐ฉ ๐น๐ญ) as well as MGSM (๐จ๐ณ ๐น๐ญ). It also surpasses GPT-3.5 in MATH CoT for Thai ๐น๐ญ.
|
24 |
+
* It scores competitively against GPT-3.5 in many zero-shot CoT commonsense benchmark, with **82.5, 68.3, 80.9** scores on Arc-C, Winogrande, and Hellaswag.
|
25 |
+
* It achieves **7.54** score on the ๐ฌ๐ง **MT-bench**, it ranks 3rd place on the leaderboard for 7B category and is the most outperforming multilingual model.
|
26 |
+
* It scores **45.74** on the VMLU benchmark for Vietnamese ๐ป๐ณ, and is the only open-source multilingual model that can be competitive to monolingual models ([Vistral-7B](https://huggingface.co/Viet-Mistral/Vistral-7B-Chat)) of similar sizes.
|
27 |
+
|
28 |
+
|
29 |
+
### Release and DEMO
|
30 |
+
|
31 |
+
- DEMO: [SeaLLMs/SeaLLM-7B](https://huggingface.co/spaces/SeaLLMs/SeaLLM-7B).
|
32 |
+
- Technical report: [Arxiv: SeaLLMs - Large Language Models for Southeast Asia](https://arxiv.org/pdf/2312.00738.pdf).
|
33 |
+
- Model weights:
|
34 |
+
- [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2).
|
35 |
+
- [SeaLLM-7B-v2-gguf](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf).
|
36 |
+
- [SeaLLM-7B-v2-GGUF (thanks Lonestriker)](https://huggingface.co/LoneStriker/SeaLLM-7B-v2-GGUF). NOTE: use [seallm.preset.json](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/seallm.preset.json) to work properly.
|
37 |
+
- Run locally:
|
38 |
+
- [LM-studio](https://lmstudio.ai/):
|
39 |
+
- [SeaLLM-7B-v2-q4_0](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/SeaLLM-7B-v2.q4_0.gguf) and [SeaLLM-7B-v2-q8_0](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/SeaLLM-7B-v2.q8_0.gguf).
|
40 |
+
- LM-studio requires this [seallm.preset.json](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/seallm.preset.json) to set chat template properly.
|
41 |
+
- [ollama](https://ollama.ai/) `ollama run nxphi47/seallm-7b-v2:q4_0`
|
42 |
+
- [MLX for Apple Silicon](https://github.com/ml-explore/mlx): [mlx-community/SeaLLM-7B-v2-4bit-mlx](https://huggingface.co/mlx-community/SeaLLM-7B-v2-4bit-mlx)
|
43 |
+
|
44 |
+
<blockquote style="color:red">
|
45 |
+
<p><strong style="color: red">Terms of Use and License</strong>:
|
46 |
+
By using our released weights, codes, and demos, you agree to and comply with the terms and conditions specified in our <a href="https://huggingface.co/SeaLLMs/SeaLLM-Chat-13b/edit/main/LICENSE" target="_blank" rel="noopener">SeaLLMs Terms Of Use</a>.
|
47 |
+
</blockquote>
|
48 |
+
|
49 |
+
> **Disclaimer**:
|
50 |
+
> We must note that even though the weights, codes, and demos are released in an open manner, similar to other pre-trained language models, and despite our best efforts in red teaming and safety fine-tuning and enforcement, our models come with potential risks, including but not limited to inaccurate, misleading or potentially harmful generation.
|
51 |
+
> Developers and stakeholders should perform their own red teaming and provide related security measures before deployment, and they must abide by and comply with local governance and regulations.
|
52 |
+
> In no event shall the authors be held liable for any claim, damages, or other liability arising from the use of the released weights, codes, or demos.
|
53 |
+
|