From 3b531a67375fd8f297cc27f4a63a69cc1cdfe373 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 9 Jul 2026 22:52:07 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: QuantFactory/SeaLLM-7B-v2-GGUF Source: Original Platform --- .gitattributes | 49 ++++++ LICENSE.txt | 53 +++++++ README.md | 333 +++++++++++++++++++++++++++++++++++++++ SeaLLM-7B-v2.Q2_K.gguf | 3 + SeaLLM-7B-v2.Q3_K_L.gguf | 3 + SeaLLM-7B-v2.Q3_K_M.gguf | 3 + SeaLLM-7B-v2.Q3_K_S.gguf | 3 + SeaLLM-7B-v2.Q4_0.gguf | 3 + SeaLLM-7B-v2.Q4_1.gguf | 3 + SeaLLM-7B-v2.Q4_K_M.gguf | 3 + SeaLLM-7B-v2.Q4_K_S.gguf | 3 + SeaLLM-7B-v2.Q5_0.gguf | 3 + SeaLLM-7B-v2.Q5_1.gguf | 3 + SeaLLM-7B-v2.Q5_K_M.gguf | 3 + SeaLLM-7B-v2.Q5_K_S.gguf | 3 + SeaLLM-7B-v2.Q6_K.gguf | 3 + SeaLLM-7B-v2.Q8_0.gguf | 3 + configuration.json | 1 + 18 files changed, 478 insertions(+) create mode 100644 .gitattributes create mode 100644 LICENSE.txt create mode 100644 README.md create mode 100644 SeaLLM-7B-v2.Q2_K.gguf create mode 100644 SeaLLM-7B-v2.Q3_K_L.gguf create mode 100644 SeaLLM-7B-v2.Q3_K_M.gguf create mode 100644 SeaLLM-7B-v2.Q3_K_S.gguf create mode 100644 SeaLLM-7B-v2.Q4_0.gguf create mode 100644 SeaLLM-7B-v2.Q4_1.gguf create mode 100644 SeaLLM-7B-v2.Q4_K_M.gguf create mode 100644 SeaLLM-7B-v2.Q4_K_S.gguf create mode 100644 SeaLLM-7B-v2.Q5_0.gguf create mode 100644 SeaLLM-7B-v2.Q5_1.gguf create mode 100644 SeaLLM-7B-v2.Q5_K_M.gguf create mode 100644 SeaLLM-7B-v2.Q5_K_S.gguf create mode 100644 SeaLLM-7B-v2.Q6_K.gguf create mode 100644 SeaLLM-7B-v2.Q8_0.gguf create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce74f7e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SeaLLM-7B-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LICENSE.txt b/LICENSE.txt new file mode 100644 index 0000000..c2a9750 --- /dev/null +++ b/LICENSE.txt @@ -0,0 +1,53 @@ +SeaLLMs LICENSE AGREEMENT +SeaLLMs Release Date: December 5, 2023 + +By clicking to agree or by using or distributing any portion or element of the SeaLLMs Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately. + +1. Definitions + a. This SeaLLMs LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement. + b. "We"(or "Us") shall mean Damo Academy. + c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use. + d. "Third Parties" shall mean individuals or legal entities that are not under common control with Us or You. + e. "SeaLLMs" shall mean the large language models (including different model versions), and software and +algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Us. + f. "Materials" shall mean, collectively, Damo Academy's proprietary SeaLLMs and Documentation (and any portion thereof) made available under this Agreement. + g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files. + h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, + and conversions to other media types. + +2. Grant of Rights +You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Damo Academy's intellectual property or other rights owned by Us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials. + +3. Redistribution +You may reproduce and distribute copies of the Materials or derivative works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: + a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement; + b. You shall cause any modified files to carry prominent notices stating that You changed the files; + c. You shall retain in all copies of the Materials that You distribute the following attribution notices within a "Notice" text file distributed as a part of such copies:"SeaLLMs is licensed under the SeaLLMs LICENSE AGREEMENT, Copyright (c) Damo Academy. All Rights Reserved."; and + d. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such derivative works as a whole, provided Your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement. + +4. Restrictions +If you are commercially using the Materials, and your product or service has more than 100 million monthly active users, You shall request a license from Us. You cannot exercise your rights under this Agreement without our express authorization. + +5. Rules of use + a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials. + b. You can not use the Materials or any output therefrom to improve any other large language model (excluding SeaLLMs or derivative works thereof). + +6. Intellectual Property + a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for Us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications. + b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of Us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials. + c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against Us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licences granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought. + +7. Disclaimer of Warranty and Limitation of Liability + + a. We are not obligated to support, update, provide training for, or develop any further version of the SeaLLMs Model or to grant any license thereto. + b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM. + c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED. + d. You will indemnify and hold harmless Us from and against any claim by any third party arising out of or related to your use or distribution of the Materials. + +8. Survival and Termination. + a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. + b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 7 and 9 shall survive the termination of this Agreement. + +9. Governing Law and Jurisdiction. + a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. + b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement. diff --git a/README.md b/README.md new file mode 100644 index 0000000..492bee1 --- /dev/null +++ b/README.md @@ -0,0 +1,333 @@ +--- +license: other +license_name: seallms +license_link: https://huggingface.co/SeaLLMs/SeaLLM-13B-Chat/blob/main/LICENSE +pipeline_tag: text-generation +tags: +- mistral +- multilingual +- sea +- conversational +base_model: SeaLLMs/SeaLLM-7B-v2 +--- + +# SeaLLM-7B-v2-GGUF +- This is GGUF quantized evrsion of [SeaLLMs/SeaLLM-7B-v2](https://huggingface.co/SeaLLMs/SeaLLM-7B-v2) + + +## Model Description + +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). + +
+

Terms of Use and License: +By using our released weights, codes, and demos, you agree to and comply with the terms and conditions specified in our SeaLLMs Terms Of Use. +

+ +> **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. + + + +### 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. + +![fig_sea_math_side_by_side.png](fig_sea_math_side_by_side.png) + + +
+See details on English and translated GSM8K and MATH with zero-shot reasoning +
+ +| Model | GSM8K
en | MATH
en | GSM8K
zh | MATH
zh | GSM8K
vi | MATH
vi | GSM8K
id | MATH
id | GSM8K
th | MATH
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 | | | | +| Qwen1.5-7B-chat | 56.8 | 15.3 | 40 | 2.7 | 37.7 | 9 | 36.9 | 7.7 | 21.9 | +| SeaLLM-7B-v2 | 78.2 | 27.5 | 53.7 | 17.6 | 69.9 | 23.8 | 71.5 | 24.4 | 59.6 | 22.4 + +
+ +Baselines were evaluated using their respective chat-template and system prompts ([Qwen1.5-7B-chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat/blob/main/tokenizer_config.json), [Vistral](https://huggingface.co/Viet-Mistral/Vistral-7B-Chat)). + +#### 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. + +| 0-shot reasoning | 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 +| Qwen1.5-7B-chat | 79.3 | 59.4 | 69.3 +| SeaLLM-7B-v2 | 82.5 | 68.3 | 80.9 + +Baselines were evaluated using their respective chat-template and system prompts ([Qwen1.5-7B-chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat/blob/main/tokenizer_config.json), [Mistral](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1)). + +### 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
MMLU | En
M3e | Zh
M3e | Vi
M3e | Vi
VMLU | Id
M3e | Th
M3e +|-----| ----- | --- | -- | ----- | ---- | --- | --- | --- | +| GPT-3.5 | Multi | 68.90 | 75.46 | 60.20 | 58.64 | 46.32 | 49.27 | 37.41 +| 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. +0-shot VMLU scores for baselines were evaluated using their respective chat-template and system prompts ([Qwen1.5-7B-chat](https://huggingface.co/Qwen/Qwen1.5-7B-Chat/blob/main/tokenizer_config.json)). + + +### 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. + +![fig_sea_bench_side_by_side.png](fig_sea_bench_side_by_side.png) + +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.<|im_start|>user +Hello world<|im_start|>assistant +Hi there, how can I help?""" + +# NOTE: previous commit has \n between 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 `` at the beginning of sequence +print(tokenizer.convert_ids_to_tokens(tokenizer.encode(prompt))) + +'', '▁<', '|', 'im', '_', 'start', '|', '>', 'system', '<0x0A>', 'You', '▁are', '▁a', '▁helpful', '▁assistant', '.', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Hello', '▁world', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>', 'Hi', '▁there', ',', '▁how', '▁can', '▁I', '▁help', '?', ''] +""" +``` + +#### 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])) +# ['', '▁<', '|', 'im', '_', 'start', '|', '>', 'system', '<0x0A>', 'You', '▁are', '▁a', '▁helpful', '▁assistant', '.', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Hello', '▁world', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>', 'Hi', '▁there', ',', '▁how', '▁can', '▁I', '▁help', '▁you', '▁today', '?', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Ex', 'plain', '▁general', '▁rel', 'ativity', '▁in', '▁details', '.', '', '▁<', '|', '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}" +TURN_PREFIX = "<|im_start|>{role}\n" + +# There is no \n between 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=['', '<|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) +``` + +#### Fine-tuning SeaLLM-7B-v2 + +Should follow the chat format and accurately mask out source tokens. Here is an example. + +```python +conversations = [ + {"role": "system", "content": "You are helful assistant."}, + {"role": "user", "content": "Hello world."}, + {"role": "assistant", "content": "Hi there, how can I help?"}, + {"role": "user", "content": "Tell me a joke."}, + {"role": "assistant", "content": "Why don't scientists trust atoms? Because they make up everything."}, +] +def seallm_7b_v2_tokenize_multi_turns(tokenizer, conversations, add_assistant_prefix=False): + """ + Inputs: + conversations: list of dict following openai format, eg + conversations = [ + {"role": "system", "content": "You are helful assistant."}, + {"role": "user", "content": "Hello world."}, + {"role": "assistant", "content": "Hi there, how can I help?"}, + {"role": "user", "content": "Tell me a joke."}, + {"role": "assistant", "content": "Why don't scientists trust atoms? Because they make up everything."}, + ] + add_assistant_prefix: whether to add assistant_prefix, only for inference decoding + Outputs: + tokenize_output_sample, { + "input_ids": ... + "token_type_ids": 1 if train and 0 if masked out (not train) + } + During training, need to create a labels, with masked-out tokens = -100 to avoid loss computations. + labels = sample['input_ids'].clone() + labels[sample['token_type_ids'] == 0] = -100 + """ + TURN_TEMPLATE = "<|im_start|>{role}\n{content}" + TURN_PREFIX = "<|im_start|>{role}\n" + sample = None + assistant_prefix_len = None + for turn_id, turn in enumerate(conversations): + prompt = TURN_TEMPLATE.format(role=turn['role'], content=turn['content']) + turn_sample = tokenizer( + prompt, padding=False, truncation=False, verbose=False, add_special_tokens=False, + return_token_type_ids=True, + ) + if turn['role'] == 'assistant': + if assistant_prefix_len is None: + assistant_prefix_len = len(tokenizer.encode(TURN_PREFIX.format(role=turn['role']), add_special_tokens=False)) + turn_sample['token_type_ids'][assistant_prefix_len:] = [1] * (len(turn_sample['input_ids']) - assistant_prefix_len) + if sample is None: + sample = turn_sample + else: + for k in turn_sample.keys(): + sample[k].extend(turn_sample[k]) + if add_assistant_prefix: + assistant_prefix_sample = tokenizer( + TURN_PREFIX.format(role="assistant"), padding=False, truncation=False, verbose=False, add_special_tokens=False, + return_token_type_ids=True, + ) + for k in sample.keys(): + sample[k].extend(assistant_prefix_sample[k]) + if tokenizer.add_bos_token: + sample['input_ids'] = [tokenizer.bos_token_id] + sample['input_ids'] + sample['attention_mask'] = [1] + sample['attention_mask'] + sample['token_type_ids'] = [sample['token_type_ids'][0]] + sample['token_type_ids'] + return sample + +# ! testing +sample = seallm_7b_v2_tokenize_multi_turns(tokenizer, conversations) +print(tokenizer.convert_ids_to_tokens(sample['input_ids'])) +print(sample['token_type_ids']) +# ['', '▁<', '|', 'im', '_', 'start', '|', '>', 'system', '<0x0A>', 'You', '▁are', '▁hel', 'ful', '▁assistant', '.', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Hello', '▁world', '.', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>', 'Hi', '▁there', ',', '▁how', '▁can', '▁I', '▁help', '?', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'user', '<0x0A>', 'Tell', '▁me', '▁a', '▁joke', '.', '', '▁<', '|', 'im', '_', 'start', '|', '>', 'ass', 'istant', '<0x0A>', 'Why', '▁don', "'", 't', '▁scientists', '▁trust', '▁atoms', '?', '▁Because', '▁they', '▁make', '▁up', '▁everything', '.', ''] +# [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1] + + + +``` + + +## 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}, +} +``` + diff --git a/SeaLLM-7B-v2.Q2_K.gguf b/SeaLLM-7B-v2.Q2_K.gguf new file mode 100644 index 0000000..50e2516 --- /dev/null +++ b/SeaLLM-7B-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df13e1b96070c6244bc57fc4bf68961b341ba010b919397809711522c6bfc6fe +size 2796713472 diff --git a/SeaLLM-7B-v2.Q3_K_L.gguf b/SeaLLM-7B-v2.Q3_K_L.gguf new file mode 100644 index 0000000..3d4dfce --- /dev/null +++ b/SeaLLM-7B-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aa3eaee6308e52c0f1b88cfd981efa5486fbf2a4de28381fd71077ff0560c7e +size 3906311680 diff --git a/SeaLLM-7B-v2.Q3_K_M.gguf b/SeaLLM-7B-v2.Q3_K_M.gguf new file mode 100644 index 0000000..c1f2338 --- /dev/null +++ b/SeaLLM-7B-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41714d5d91271820f96cb8c3c2021d0229fd38f03c65d5e0ad663502e0316751 +size 3603273216 diff --git a/SeaLLM-7B-v2.Q3_K_S.gguf b/SeaLLM-7B-v2.Q3_K_S.gguf new file mode 100644 index 0000000..5efd31c --- /dev/null +++ b/SeaLLM-7B-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d40510d1b8a46515e44d22d1c910847cf3706819bea15ffda3fac45bbaac83 +size 3248854528 diff --git a/SeaLLM-7B-v2.Q4_0.gguf b/SeaLLM-7B-v2.Q4_0.gguf new file mode 100644 index 0000000..1fb9dac --- /dev/null +++ b/SeaLLM-7B-v2.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247c8a361c692b6f4ad67132ab3bf90d9fe27c90dc5a377c3c939f0de9969d77 +size 4202116608 diff --git a/SeaLLM-7B-v2.Q4_1.gguf b/SeaLLM-7B-v2.Q4_1.gguf new file mode 100644 index 0000000..a3e3300 --- /dev/null +++ b/SeaLLM-7B-v2.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be598ae0919e0cb71e6d55563e524a99176684cf000cad488554baaf04ee693 +size 4650710528 diff --git a/SeaLLM-7B-v2.Q4_K_M.gguf b/SeaLLM-7B-v2.Q4_K_M.gguf new file mode 100644 index 0000000..b5c9673 --- /dev/null +++ b/SeaLLM-7B-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f562d8235884f38a549413f3d5a7ed23cc86dd51b5a05ade872f6db7200944f9 +size 4461639168 diff --git a/SeaLLM-7B-v2.Q4_K_S.gguf b/SeaLLM-7B-v2.Q4_K_S.gguf new file mode 100644 index 0000000..0528e6c --- /dev/null +++ b/SeaLLM-7B-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd27d0352911b4574eb99b72229f93debbb20c11f1d0fba444bbe0073630c4d1 +size 4233573888 diff --git a/SeaLLM-7B-v2.Q5_0.gguf b/SeaLLM-7B-v2.Q5_0.gguf new file mode 100644 index 0000000..0a49a79 --- /dev/null +++ b/SeaLLM-7B-v2.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85c44555326e953367769e229c77243b38e17d1bd9096b97d6d65342b99243b6 +size 5099304448 diff --git a/SeaLLM-7B-v2.Q5_1.gguf b/SeaLLM-7B-v2.Q5_1.gguf new file mode 100644 index 0000000..5c37d7d --- /dev/null +++ b/SeaLLM-7B-v2.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9662a3ba0a0a1a01764fa435b4fac22443925ea378e28cd13a4bdd678387a9 +size 5547898368 diff --git a/SeaLLM-7B-v2.Q5_K_M.gguf b/SeaLLM-7B-v2.Q5_K_M.gguf new file mode 100644 index 0000000..2c6e941 --- /dev/null +++ b/SeaLLM-7B-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c168c7f79aa46bae74e1556389f03a83d77c3a22a1b4007a884b90e511c6e3ef +size 5232997888 diff --git a/SeaLLM-7B-v2.Q5_K_S.gguf b/SeaLLM-7B-v2.Q5_K_S.gguf new file mode 100644 index 0000000..edb8139 --- /dev/null +++ b/SeaLLM-7B-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624d1fb8795e0f64d9613f46a1ba87cba055e3ee591053082fb59a0ed21cc543 +size 5099304448 diff --git a/SeaLLM-7B-v2.Q6_K.gguf b/SeaLLM-7B-v2.Q6_K.gguf new file mode 100644 index 0000000..1c0d36b --- /dev/null +++ b/SeaLLM-7B-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2c429b56d55096568b441145121b4b0d2b5892d28f461e630c31a295d26cb9 +size 6052566528 diff --git a/SeaLLM-7B-v2.Q8_0.gguf b/SeaLLM-7B-v2.Q8_0.gguf new file mode 100644 index 0000000..d3f0489 --- /dev/null +++ b/SeaLLM-7B-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa87b9074c479f23339f359dd52efd57fe2a6a0cac504e80acb7b7be93f7e74a +size 7838864896 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file