|
--- |
|
license: other |
|
license_name: seallms |
|
license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE |
|
--- |
|
# *SeaLLM-7B-v2* - Large Language Models for Southeast Asia |
|
|
|
**NOTE: download [seallm.preset.json](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/seallm.preset.json) for LM-studio to work correctly,** |
|
|
|
<p align="center"> |
|
<a href="https://huggingface.co/SeaLLMs/SeaLLM-7B-v2" target="_blank" rel="noopener"> 🤗 Tech Memo</a> |
|
|
|
<a href="https://huggingface.co/spaces/SeaLLMs/SeaLLM-7B" target="_blank" rel="noopener"> 🤗 DEMO</a> |
|
|
|
<a href="https://github.com/DAMO-NLP-SG/SeaLLMs" target="_blank" rel="noopener">Github</a> |
|
|
|
<a href="https://arxiv.org/pdf/2312.00738.pdf" target="_blank" rel="noopener">Technical Report</a> |
|
</p> |
|
|
|
We introduce [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2), the state-of-the-art multilingual LLM for Southeast Asian (SEA) languages 🇬🇧 🇨🇳 🇻🇳 🇮🇩 🇹🇭 🇲🇾 🇰🇭 🇱🇦 🇲🇲 🇵🇭. 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. |
|
|
|
### Highlights |
|
* [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 (🇨🇳 🇻🇳 🇮🇩 🇹🇭) as well as MGSM (🇨🇳 🇹🇭). It also surpasses GPT-3.5 in MATH CoT for Thai 🇹🇭. |
|
* 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. |
|
* It achieves **7.54** score on the 🇬🇧 **MT-bench**, it ranks 3rd place on the leaderboard for 7B category and is the most outperforming multilingual model. |
|
* It scores **45.74** on the VMLU benchmark for Vietnamese 🇻🇳, 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. |
|
|
|
|
|
### Release and DEMO |
|
|
|
- DEMO: [SeaLLMs/SeaLLM-7B](https://huggingface.co/spaces/SeaLLMs/SeaLLM-7B). |
|
- Technical report: [Arxiv: SeaLLMs - Large Language Models for Southeast Asia](https://arxiv.org/pdf/2312.00738.pdf). |
|
- Model weights: |
|
- [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2). |
|
- [SeaLLM-7B-v2-gguf](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf). |
|
- [SeaLLM-7B-v2-q4_0](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/SeaLLM-7B-v2.q4_0.gguf), [SeaLLM-7B-v2-q8_0](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/SeaLLM-7B-v2.q8_0.gguf). |
|
- LM-studio requires this [seallm.preset.json](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2-gguf/blob/main/seallm.preset.json) to work properly. |
|
- [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. |
|
|
|
|
|
<blockquote style="color:red"> |
|
<p><strong style="color: red">Terms of Use and License</strong>: |
|
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>. |
|
</blockquote> |
|
|
|
> **Disclaimer**: |
|
> 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. |
|
> 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. |
|
> 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. |
|
|
|
> The logo was generated by DALL-E 3. |
|
|
|
|
|
### What's new since SeaLLM-13B-v1 and SeaLLM-7B-v1? |
|
|
|
* SeaLLM-7B-v2 is continue-pretrained from [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1) and underwent carefully designed tuning with focus in reasoning. |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
### Zero-shot CoT Multilingual Math Reasoning |
|
|
|
[SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) achieves with **78.2** score on the GSM8K with zero-shot CoT reasoning, making it the **state of the art** in the realm of 7B models. It also outperforms GPT-3.5 in the same GSM8K benchmark as translated into SEA languages (🇨🇳 🇻🇳 🇮🇩 🇹🇭). [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) also surpasses GPT-3.5 on the Thai-translated MATH benchmark, with **22.4** vs 18.1 scores. |
|
|
|
 |
|
|
|
|
|
<details> |
|
<summary>See details on English and translated GSM8K and MATH with zero-shot reasoning</summary> |
|
<br> |
|
|
|
| Model | GSM8K<br>en | MATH<br>en | GSM8K<br>zh | MATH<br>zh | GSM8K<br>vi | MATH<br>vi | GSM8K<br>id | MATH<br>id | GSM8K<br>th | MATH<br>th |
|
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | |
|
| GPT-3.5 | 80.8 | 34.1 | 48.2 | 21.5 | 55 | 26.5 | 64.3 | 26.4 | 35.8 | 18.1 |
|
| Qwen-14B-chat | 61.4 | 18.4 | 41.6 | 11.8 | 33.6 | 3.6 | 44.7 | 8.6 | 22 | 6 |
|
| Vistral-7b-chat | 48.2 | 12.5 | | | 48.7 | 3.1 | | | | |
|
| SeaLLM-7B-v2 | 78.2 | 27.5 | 53.7 | 17.6 | 69.9 | 23.8 | 71.5 | 24.4 | 59.6 | 22.4 |
|
|
|
</details> |
|
|
|
#### Zero-shot MGSM |
|
|
|
[SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) also outperforms GPT-3.5 and Qwen-14B on the multilingual MGSM for Zh and Th. |
|
|
|
| Model | MGSM-Zh | MGSM-Th |
|
|-----| ----- | --- |
|
| ChatGPT (reported) | 61.2* | 47.2* |
|
| Qwen-14B-chat | 59.6 | 28 |
|
| SeaLLM-7B-v2 | **64.8** | **62.4** |
|
|
|
|
|
### Zero-shot Commonsense Reasoning |
|
|
|
We compare [SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) with ChatGPT and Mistral-7B-instruct on various zero-shot commonsense benchmarks (Arc-Challenge, Winogrande and Hellaswag). We use the 2-stage technique in [(Kojima et al., 2023)](https://arxiv.org/pdf/2205.11916.pdf) to grab the answer. Note that we **DID NOT** use "Let's think step-by-step" to invoke explicit CoT. |
|
|
|
| Model | Arc-Challenge | Winogrande | Hellaswag |
|
|-----| ----- | --- | -- | |
|
| ChatGPT (reported) | 84.6* | 66.8* | 72.0* |
|
| ChatGPT (reproduced) | 84.1 | 63.1 | 79.5 |
|
| Mistral-7B-Instruct | 68.1 | 56.4 | 45.6 |
|
| SeaLLM-7B-v2 | 82.5 | 68.3 | 80.9 |
|
|
|
|
|
### Multilingual World Knowledge |
|
|
|
|
|
We evaluate models on 3 benchmarks following the recommended default setups: 5-shot MMLU for En, 3-shot [M3Exam](https://arxiv.org/pdf/2306.05179.pdf) (M3e) for En, Zh, Vi, Id, Th, and zero-shot [VMLU](https://vmlu.ai/) for Vi. |
|
|
|
| Model | Langs | En<br>MMLU | En<br>M3e | Zh<br>M3e | Vi<br>M3e | Vi<br>VMLU | Id<br>M3e | Th<br>M3e |
|
|-----| ----- | --- | -- | ----- | ---- | --- | --- | --- | |
|
| GPT-3.5 | Multi | 68.90 | 75.46 | 60.20 | 58.64 | 46.32 | 49.27 | 37.41 |
|
| SeaLLM-13B | Multi | 52.78 | 62.69 | 44.50 | 46.45 | | 39.28 | 36.39 |
|
| Vistral-7B-chat | Mono | 56.86 | 67.00 | 44.56 | 54.33 | 50.03 | 36.49 | 25.27 |
|
| Qwen1.5-7B-chat | Multi | 61.00 | 52.07 | 81.96 | 43.38 | 45.02 | 24.29 | 20.25 |
|
| SeaLLM-7B-v2 | Multi | 61.89 | 70.91 | 55.43 | 51.15 | 45.74 | 42.25 | 35.52 |
|
|
|
VMLU reproduce script [here](https://github.com/DAMO-NLP-SG/SeaLLMs/blob/main/evaluation/vmlu/vmlu_run.py). Lm-eval was used to evaluate MMLU. |
|
|
|
|
|
### MT-Bench |
|
|
|
On the English [MT-bench](https://arxiv.org/abs/2306.05685) metric, SeaLLM-7B-v2 achieves **7.54** score on the MT-bench (3rd place on the leaderboard for 7B category), outperforms many 70B models and is arguably the only one that handles 10 SEA languages. |
|
|
|
Refer to [mt_bench/seallm_7b_v2.jsonl](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2/blob/main/evaluation/mt_bench/seallm_7b_v2.jsonl) for the MT-bench predictions of SeaLLM-7B-v2, and [here](https://github.com/lm-sys/FastChat/issues/3013#issue-2118685341) to reproduce it. |
|
|
|
| Model | Access | Langs | MT-Bench |
|
| --- | --- | --- | --- | |
|
| GPT-4-turbo | closed | multi | 9.32 |
|
| GPT-4-0613 | closed | multi | 9.18 |
|
| Mixtral-8x7b (46B) | open | multi | 8.3 |
|
| Starling-LM-7B-alpha | open | mono (en) | 8.0 |
|
| OpenChat-3.5-7B | open | mono (en) | 7.81 |
|
| **SeaLLM-7B-v2** | **open** | **multi (10+)** | **7.54** |
|
| [Qwen-14B](https://huggingface.co/Qwen/Qwen-14B-Chat) | open | multi | 6.96 |
|
| [Llama-2-70B](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf) | open | mono (en) | 6.86 |
|
| Mistral-7B-instuct | open | mono (en) | 6.84 |
|
|
|
|
|
### Sea-Bench |
|
|
|
Similar to MT-Bench, [Sea-bench](https://huggingface.co/datasets/SeaLLMs/Sea-bench) is a set of categorized instruction test sets to measure models' ability as an assistant that is specifically focused on 9 SEA languages, including non-Latin low-resource languages. |
|
|
|
As shown, the huge improvements come from math-reasoning, reaching GPT-3.5 level of performance. |
|
|
|
 |
|
|
|
Refer to [sea_bench/seallm_7b_v2.jsonl](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2/blob/main/evaluation/sea_bench/seallm_7b_v2.jsonl) for the Sea-bench predictions of SeaLLM-7B-v2. |
|
|
|
|
|
|
|
### Usage |
|
|
|
#### Instruction format |
|
|
|
```python |
|
prompt = """<|im_start|>system |
|
You are a helpful assistant.</s><|im_start|>user |
|
Hello world</s><|im_start|>assistant |
|
Hi there, how can I help?</s>""" |
|
|
|
# NOTE: previous commit has \n between </s> and <|im_start|>, that was incorrect! |
|
# <|im_start|> is not a special token. |
|
# Transformers chat_template should be consistent with vLLM format below. |
|
|
|
# ! ENSURE 1 and only 1 bos `<s>` at the beginning of sequence |
|
print(tokenizer.convert_ids_to_tokens(tokenizer.encode(prompt))) |
|
|
|
'<s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'system', '<0x0A>', 'You', '▁are', '▁a', '▁helpful', '▁assistant', '.', '</s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Hello', '▁world', '</s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>', 'Hi', '▁there', ',', '▁how', '▁can', '▁I', '▁help', '?', '</s>'] |
|
""" |
|
``` |
|
|
|
#### Using transformers's chat_template |
|
```python |
|
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
device = "cuda" # the device to load the model onto |
|
|
|
# use bfloat16 to ensure the best performance. |
|
model = AutoModelForCausalLM.from_pretrained("SeaLLMs/SeaLLM-7B-v2", torch_dtype=torch.bfloat16, device_map=device) |
|
tokenizer = AutoTokenizer.from_pretrained("SeaLLMs/SeaLLM-7B-v2") |
|
|
|
messages = [ |
|
{"role": "system", "content": "You are a helpful assistant."}, |
|
{"role": "user", "content": "Hello world"}, |
|
{"role": "assistant", "content": "Hi there, how can I help you today?"}, |
|
{"role": "user", "content": "Explain general relativity in details."} |
|
] |
|
|
|
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True) |
|
print(tokenizer.convert_ids_to_tokens(encodeds[0])) |
|
# ['<s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'system', '<0x0A>', 'You', '▁are', '▁a', '▁helpful', '▁assistant', '.', '</s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Hello', '▁world', '</s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>', 'Hi', '▁there', ',', '▁how', '▁can', '▁I', '▁help', '▁you', '▁today', '?', '</s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Ex', 'plain', '▁general', '▁rel', 'ativity', '▁in', '▁details', '.', '</s>', '▁<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>'] |
|
|
|
model_inputs = encodeds.to(device) |
|
model.to(device) |
|
|
|
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True, pad_token_id=tokenizer.pad_token_id) |
|
decoded = tokenizer.batch_decode(generated_ids) |
|
print(decoded[0]) |
|
|
|
``` |
|
|
|
#### Using vLLM |
|
|
|
```python |
|
from vllm import LLM, SamplingParams |
|
TURN_TEMPLATE = "<|im_start|>{role}\n{content}</s>" |
|
TURN_PREFIX = "<|im_start|>{role}\n" |
|
|
|
# There is no \n between </s> and <|im_start|>. |
|
|
|
def seallm_chat_convo_format(conversations, add_assistant_prefix: bool, system_prompt=None): |
|
# conversations: list of dict with key `role` and `content` (openai format) |
|
if conversations[0]['role'] != 'system' and system_prompt is not None: |
|
conversations = [{"role": "system", "content": system_prompt}] + conversations |
|
text = '' |
|
for turn_id, turn in enumerate(conversations): |
|
prompt = TURN_TEMPLATE.format(role=turn['role'], content=turn['content']) |
|
text += prompt |
|
if add_assistant_prefix: |
|
prompt = TURN_PREFIX.format(role='assistant') |
|
text += prompt |
|
return text |
|
|
|
sparams = SamplingParams(temperature=0.1, max_tokens=1024, stop=['</s>', '<|im_start|>']) |
|
llm = LLM("SeaLLMs/SeaLLM-7B-v2", dtype="bfloat16") |
|
|
|
message = "Explain general relativity in details." |
|
prompt = seallm_chat_convo_format(message, True) |
|
gen = llm.generate(prompt, sampling_params) |
|
|
|
print(gen[0].outputs[0].text) |
|
``` |
|
|
|
|
|
## Acknowledgement to Our Linguists |
|
|
|
We would like to express our special thanks to our professional and native linguists, Tantong Champaiboon, Nguyen Ngoc Yen Nhi and Tara Devina Putri, who helped build, evaluate, and fact-check our sampled pretraining and SFT dataset as well as evaluating our models across different aspects, especially safety. |
|
|
|
## Citation |
|
|
|
If you find our project useful, we hope you would kindly star our repo and cite our work as follows: Corresponding Author: [l.bing@alibaba-inc.com](mailto:l.bing@alibaba-inc.com) |
|
|
|
**Author list and order will change!** |
|
|
|
* `*` and `^` are equal contributions. |
|
|
|
``` |
|
@article{damonlpsg2023seallm, |
|
author = {Xuan-Phi Nguyen*, Wenxuan Zhang*, Xin Li*, Mahani Aljunied*, |
|
Zhiqiang Hu, Chenhui Shen^, Yew Ken Chia^, Xingxuan Li, Jianyu Wang, |
|
Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, |
|
Chaoqun Liu, Hang Zhang, Lidong Bing}, |
|
title = {SeaLLMs - Large Language Models for Southeast Asia}, |
|
year = 2023, |
|
Eprint = {arXiv:2312.00738}, |
|
} |
|
``` |
|
|
|
|
