munish0838 commited on
Commit
71c9cca
ยท
verified ยท
1 Parent(s): fddf034

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -0
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 ๐Ÿ‡ฌ๐Ÿ‡ง ๐Ÿ‡จ๐Ÿ‡ณ ๐Ÿ‡ป๐Ÿ‡ณ ๐Ÿ‡ฎ๐Ÿ‡ฉ ๐Ÿ‡น๐Ÿ‡ญ ๐Ÿ‡ฒ๐Ÿ‡พ ๐Ÿ‡ฐ๐Ÿ‡ญ ๐Ÿ‡ฑ๐Ÿ‡ฆ ๐Ÿ‡ฒ๐Ÿ‡ฒ ๐Ÿ‡ต๐Ÿ‡ญ. 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 (๐Ÿ‡จ๐Ÿ‡ณ ๐Ÿ‡ป๐Ÿ‡ณ ๐Ÿ‡ฎ๐Ÿ‡ฉ ๐Ÿ‡น๐Ÿ‡ญ) as well as MGSM (๐Ÿ‡จ๐Ÿ‡ณ ๐Ÿ‡น๐Ÿ‡ญ). It also surpasses GPT-3.5 in MATH CoT for Thai ๐Ÿ‡น๐Ÿ‡ญ.
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 ๐Ÿ‡ฌ๐Ÿ‡ง **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 ๐Ÿ‡ป๐Ÿ‡ณ, 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
+