初始化项目，由ModelHub XC社区提供模型
Model: chienweichang/Llama-3-Taiwan-8B-Instruct-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
67
.gitattributes
vendored
Normal file
67
.gitattributes
vendored
Normal file
@@ -0,0 +1,67 @@
|
||||
*.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
|
||||
llama3-3-taiwan-8B-instruct-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama3-3-taiwan-8B-instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q5_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
llama-3-taiwan-8B-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
345
README.md
Normal file
345
README.md
Normal file
@@ -0,0 +1,345 @@
|
||||
---
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
base_model: yentinglin/Llama-3-Taiwan-8B-Instruct
|
||||
tags:
|
||||
- zhtw
|
||||
license: llama3
|
||||
---
|
||||
|
||||
## Description
|
||||
|
||||
This repo contains GGUF format model files for [yentinglin/Llama-3-Taiwan-8B-Instruct](https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct).
|
||||
|
||||
|
||||
## Provided files
|
||||
| Name | Quant method | Bits | Size | Use case |
|
||||
| ---- | ---- | ---- | ---- | ---- |
|
||||
| [llama-3-taiwan-8b-instruct-q5_0.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-8B-Instruct-GGUF/blob/main/llama-3-taiwan-8B-instruct-q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality |
|
||||
| [llama-3-taiwan-8b-instruct-q5_1.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-8B-Instruct-GGUF/blob/main/llama-3-taiwan-8B-instruct-q5_1.gguf) | Q5_1 | 5 | 6.07 GB| large, low quality loss |
|
||||
| [llama-3-taiwan-8b-instruct-q5_k_s.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-8B-Instruct-GGUF/blob/main/llama-3-taiwan-8B-instruct-q5_k_s.gguf) | Q5_K_S | 5 | 5.6 GB| large, very low quality loss |
|
||||
| [llama-3-taiwan-8b-instruct-q5_k_m.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-8B-Instruct-GGUF/blob/main/llama-3-taiwan-8B-instruct-q5_k_m.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss |
|
||||
| [llama-3-taiwan-8b-instruct-q6_k.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-8B-Instruct-GGUF/blob/main/llama-3-taiwan-8B-instruct-q6_k.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss |
|
||||
| [llama-3-taiwan-8b-instruct-q8_0.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-8B-Instruct-GGUF/blob/main/llama-3-taiwan-8B-instruct-q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss |
|
||||
|
||||
## Original model card
|
||||
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/5df9c78eda6d0311fd3d541f/vlfv5sHbt4hBxb3YwULlU.png" alt="Taiwan LLM Logo" width="600" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
||||
|
||||
# 🚀 [Demo Site](https://twllm.com/)
|
||||
|
||||
Try out Llama-3-Taiwan interactively at [twllm.com](https://twllm.com/)
|
||||
|
||||
# ⚔️ [Chatbot Arena](https://arena.twllm.com/)
|
||||
|
||||
Participate in the exciting [Chatbot Arena](https://arena.twllm.com/) and compete against other chatbots!
|
||||
|
||||
🚀 We're excited to introduce Llama-3-Taiwan-70B! Llama-3-Taiwan-70B is a 70B parameter model finetuned on a large corpus of Traditional Mandarin and English data using the Llama-3 architecture. It demonstrates state-of-the-art performance on various Traditional Mandarin NLP benchmarks.
|
||||
|
||||
The model was trained with [NVIDIA NeMo™ Framework](https://www.nvidia.com/en-us/ai-data-science/generative-ai/nemo-framework/) using the NVIDIA Taipei-1 built with [NVIDIA DGX H100](https://www.nvidia.com/en-us/data-center/dgx-h100/) systems.
|
||||
|
||||
The compute and data for training Llama-3-Taiwan-70B was generously sponsored by [Chang Gung Memorial Hospital](https://www.cgmh.org.tw/eng), [Chang Chun Group](https://www.ccp.com.tw/ccpweb.nsf/homepage?openagent), [Legalsign.ai](https://legalsign.ai/), [NVIDIA](https://www.nvidia.com/zh-tw/), [Pegatron](https://www.pegatroncorp.com/), [TechOrange](https://buzzorange.com/techorange/), and [Unimicron](https://www.unimicron.com/) (in alphabetical order).
|
||||
|
||||
We would like to acknowledge the [contributions](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc1#contributions) of our data provider, team members and advisors in the development of this model, including [shasha77](https://www.youtube.com/@shasha77) for high-quality YouTube scripts and study materials, [Taiwan AI Labs](https://ailabs.tw/) for providing local media content, [Ubitus K.K.](https://ubitus.net/zh/) for offering gaming content, Professor Yun-Nung (Vivian) Chen for her guidance and advisement, Wei-Lin Chen for leading our pretraining data pipeline, Tzu-Han Lin for synthetic data generation, Chang-Sheng Kao for enhancing our synthetic data quality, and Kang-Chieh Chen for cleaning instruction-following data.
|
||||
|
||||
|
||||
# Model Summary
|
||||
|
||||
Llama-3-Taiwan-70B is a large language model finetuned for Traditional Mandarin and English users. It has strong capabilities in language understanding, generation, reasoning, and multi-turn dialogue. Key features include:
|
||||
|
||||
- 70B parameters
|
||||
- Languages: Traditional Mandarin (zh-tw), English (en)
|
||||
- Finetuned on High-quality Traditional Mandarin and English corpus covering general knowledge as well as industrial knowledge in legal, manufacturing, medical, and electronics domains
|
||||
- 8K context length
|
||||
- Open model released under the Llama-3 license
|
||||
|
||||
# Training Details
|
||||
|
||||
- Training Framework: [NVIDIA NeMo](https://www.nvidia.com/zh-tw/ai-data-science/products/nemo/), [NVIDIA NeMo Megatron](https://docs.nvidia.com/nemo-framework/user-guide/latest/nemotoolkit/nlp/megatron.html)
|
||||
- Inference Framework: [NVIDIA TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM)
|
||||
- Base model: [Llama-3 70B](https://llama.meta.com/llama3/)
|
||||
- Hardware: [NVIDIA DGX H100](https://www.nvidia.com/zh-tw/data-center/dgx-h100/) on Taipei-1
|
||||
- Context length: 8K tokens ([128k version](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-128k))
|
||||
- Batch size: 2M tokens per step
|
||||
|
||||
# Evaluation
|
||||
|
||||
Checkout [Open TW LLM Leaderboard](https://huggingface.co/spaces/yentinglin/open-tw-llm-leaderboard) for full and updated list.
|
||||
|
||||
| Model | [TMLU](https://arxiv.org/pdf/2403.20180) | Taiwan Truthful QA | [Legal Eval](https://huggingface.co/datasets/lianghsun/tw-legal-benchmark-v1) | [TW MT-Bench](https://huggingface.co/datasets/MediaTek-Research/TCEval-v2) | Long context | Function Calling | [TMMLU+](https://github.com/iKala/ievals) |
|
||||
|---------------------------------------------------------------------------------|--------------|---------------|--------------------|--------------|--------------|-----------------|-----------|
|
||||
| | 學科知識 | 台灣在地化測試 | 台灣法律考題 | 中文多輪對答 | 長文本支援 | 函數呼叫 | |
|
||||
| [**yentinglin/Llama-3-Taiwan-70B-Instruct**](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct) | **74.76%** | 80.95% | 68.42% | 7.54 | [128k version](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-128k) | ✅ | 67.53% |
|
||||
| [**yentinglin/Llama-3-Taiwan-70B-Instruct-DPO**](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-DPO) | 74.60% | **81.75%** | **70.33%** | - | - | ✅ | - |
|
||||
| [**yentinglin/Llama-3-Taiwan-70B-Instruct-128k**](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct) | 73.01% | 80.16% | 63.64% | - | - | ✅ | - |
|
||||
| [**yentinglin/Llama-3-Taiwan-8B-Instruct**](https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct) | 59.50% | 61.11% | 53.11% | 7.21 | [128k version](https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-128k) | ✅ | 52.28% |
|
||||
| [**yentinglin/Llama-3-Taiwan-8B-Instruct-DPO**](https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-DPO) | 59.88% | 59.52% | 52.63% | - | - | ✅ | - |
|
||||
| [**yentinglin/Llama-3-Taiwan-8B-Instruct-128k**](https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-128k) | - | - | - | - | - | ✅ | - |
|
||||
| [Claude-3-Opus](https://www.anthropic.com/api) | [73.59% (5-shot)](https://arxiv.org/pdf/2403.20180) | [69.84%](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc3/tree/main/opus-Taiwan-Truthful-QA) | [60.29%](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc3/tree/main/opus) | - | 200k | ✅ | - |
|
||||
| [GPT4-o](https://platform.openai.com/docs/api-reference/chat/create) | [65.56% (0-shot), 69.88% (5-shot)](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc3/tree/main/4o-tmlu) | [76.98%](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc3/tree/main/4o-Taiwan-Truthful-QA) | [53.59%](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc3/tree/main/4o) | - | 128k | ✅ | - |
|
||||
| [GPT4-turbo](https://platform.openai.com/docs/api-reference/chat/create) | [70.42% (5-shot)](https://arxiv.org/pdf/2403.20180) | - | - | - | 128k | ✅ | 60.34%^ |
|
||||
| [Gemini-Pro](https://ai.google.dev/gemini-api/docs) | [61.40% (5-shot)](https://arxiv.org/pdf/2403.20180) | - | - | - | 1000k | ✅ | 49.92%^ |
|
||||
| [GPT-3.5-turbo-1106](https://platform.openai.com/docs/api-reference/chat/create) | [49.37% (5-shot)](https://arxiv.org/pdf/2403.20180) | - | - | 7.1 | 128k | ✅ | 41.76%^ |
|
||||
| [Qwen1.5-110B-Chat](https://huggingface.co/Qwen/Qwen1.5-110B-Chat) | **75.69%** | 66.67% | 49.28% | - | 32k | ✅ | 65.81% |
|
||||
| [Yi-34B-Chat](https://huggingface.co/01-ai/Yi-34B-Chat) | 73.59% | 71.43% | 55.02% | 6.9 | 200k | ✅ | 64.10% |
|
||||
| [Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) | 70.95% | 65.08% | 52.63% | - | 8k | ✅ | 62.75% |
|
||||
| [Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1) | 55.57% | 52.38% | 44.98% | - | 64k | ✅ | 52.16% |
|
||||
| [Breexe-8x7B-Instruct-v0_1](https://huggingface.co/MediaTek-Research/Breexe-8x7B-Instruct-v0_1) | - | - | - | 7.2 | 8k | ❓ | 48.92% |
|
||||
| [c4ai-command-r-plus](https://huggingface.co/CohereForAI/c4ai-command-r-plus) | 62.87% | 64.29% | 34.45% | - | 128k | ✅ | 49.75% |
|
||||
| [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | 55.81% | 46.83% | 35.89% | - | 8k | ✅ | 43.38% |
|
||||
| [Breeze-7B-Instruct-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0) | 55.57% | 52.38% | 39.23% | 6.0 | 32k | ❓ | 41.77% |
|
||||
| [Llama3-TAIDE-LX-8B-Chat-Alpha1](https://huggingface.co/taide/Llama3-TAIDE-LX-8B-Chat-Alpha1) | 47.30% | 50.79% | 37.80% | - | 8k | ❓ | 39.03% |
|
||||
| [Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) | 40.97% | 37.30% | 27.27% | - | 4k | ❓ | 33.02% |
|
||||
|
||||
Numbers are 0-shot by default.
|
||||
|
||||
[Eval implementation](https://github.com/adamlin120/lm-evaluation-harness)
|
||||
|
||||
^ taken the closet matching numbers from original dataset.
|
||||
|
||||
## Needle in a Haystack Evaluation
|
||||
|
||||
The "Needle in a 出師表" evaluation tests the model's ability to locate and recall important information embedded within a large body of text, using the classic Chinese text 《出師表》 by 諸葛亮.
|
||||
|
||||
To run the evaluation, use the [script](https://github.com/adamlin120/needle-haystack/tree/main).
|
||||
|
||||
|
||||
# TW MT-Bench Score
|
||||
|
||||
- Average Score: 7.5375
|
||||
- Maximum Score: 10
|
||||
- Minimum Score: 1
|
||||
- Median Score: 9.0
|
||||
- Standard Deviation: 3.0349783771882133
|
||||
- Total Number of Scores: 160
|
||||
- [Model resopnse](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc1/blob/main/Llama-3-Taiwan.jsonl)
|
||||
- [GPT-4 Eval](https://huggingface.co/yentinglin/Llama-3-Taiwan-70B-Instruct-rc1/blob/main/gpt-4_single.jsonl)
|
||||
- [Code fork from `mtkresearch/TCEval` with bug fixing](https://github.com/adamlin120/TCEval)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# Use Cases
|
||||
|
||||
Llama-3-Taiwan-70B can be applied to a wide variety of NLP tasks in Traditional Chinese and English, including:
|
||||
|
||||
<details>
|
||||
<summary>1. 多輪對話</summary>
|
||||
|
||||
<pre>
|
||||
System: You are an AI assistant called Twllm, created by TAME (TAiwan Mixture of Expert) project.
|
||||
|
||||
User: 嗨，你好！
|
||||
|
||||
Assistant: 你好！我今天可以如何協助你？
|
||||
|
||||
User: 就想聊天而已....
|
||||
|
||||
Assistant: 當然，我很樂意和你聊天！有什麼特別想談論的嗎？
|
||||
</pre>
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>2. RAG（檢索增強生成）</summary>
|
||||
|
||||
Demo: 可以打開 `Search Web` on [twllm.com](https://twllm.com/)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<pre>
|
||||
System: You are an AI assistant called Twllm, created by TAME (TAiwan Mixture of Expert) project.
|
||||
|
||||
User: 明天台大天氣如何？
|
||||
|
||||
Assistant: 根據天氣預報，明天台大天氣為陣雨。低溫 24°C。10 到 15 公里/小時 的 東 風 。降雨機率為 40%。
|
||||
</pre>
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>3. 格式化輸出, 語言理解, 實體識別, 函數調用</summary>
|
||||
|
||||
If you are interested in function-calling, I strongly recommend [using constrained decoding](https://huggingface.co/docs/text-generation-inference/basic_tutorials/using_guidance) to turn on `json mode`.
|
||||
|
||||
Example from HW7 in `INTRODUCTION TO GENERATIVE AI 2024 SPRING` from `HUNG-YI LEE (李宏毅)`
|
||||
|
||||
|
||||
|
||||
|
||||
<pre>
|
||||
System: You are an AI assistant called Twllm, created by TAME (TAiwan Mixture of Expert) project.
|
||||
|
||||
User: 您是電影評論分析師，負責情緒分析。
|
||||
分析每個被評論的句子，評估句子中每個字和標點符號的重要性，
|
||||
並且將結果使用 tuple 的結構列出。
|
||||
tuple 值的範圍介於 -1 (負向) 到 1 (正向) 之間，
|
||||
然後，將評論分類為正向 (1) 或負向 (-1)。
|
||||
這些需要被評論的句子，包含在 <review> 標籤中間。
|
||||
|
||||
輸出範例:
|
||||
[(<單字或標點符號>, <float importance>), ...]
|
||||
<int classification>
|
||||
<review> 根據外媒報導，宏都拉斯在去年3月與台灣斷交，並轉往與中國建交之後，卻遲遲等不到中國的金援，談好要進口宏都拉斯的白蝦也拖延許久，甚至還將白蝦價格殺價至過往與台灣交易的半價，再加上墨西哥同時也中斷了與宏國的白蝦貿易，對當地蝦農可說是雪上加霜。 <review>
|
||||
|
||||
|
||||
Assistant: [('根據', 0.2), ('外媒', 0.1), ('報導', -0.1), (',', 0.05), ('宏都拉斯', -0.3), ('在去年3月與台灣斷交， ', -0.5), ('並轉往與中國建交之後， ', -0.4), ('卻遲遲等不到中國的金援， ', -1),
|
||||
('談好要進口宏都拉斯的白蝦也拖延許久， ', -1),
|
||||
(',甚至還將白蝦價格殺價至過往與台灣交易的半價，再加上墨西哥同時也中斷了與宏國的白蝦貿易，對當地蝦農可說是雪上加霜。 ',-1)]
|
||||
-1
|
||||
|
||||
</pre>
|
||||
</details>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# Get Started
|
||||
|
||||
*Caveat: System message should always be set.*
|
||||
|
||||
## Hugging Face Transformers library
|
||||
You can use Llama-3-Taiwan-70B with the Hugging Face Transformers library:
|
||||
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import pipeline, StoppingCriteria
|
||||
|
||||
# Define a custom stopping criteria class
|
||||
class EosListStoppingCriteria(StoppingCriteria):
|
||||
def __init__(self, eos_sequence=[128256]):
|
||||
self.eos_sequence = eos_sequence
|
||||
|
||||
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
|
||||
last_ids = input_ids[:, -len(self.eos_sequence):].tolist()
|
||||
return self.eos_sequence in last_ids
|
||||
|
||||
# Initialize the model with automatic device mapping
|
||||
llm = pipeline("text-generation", model="yentinglin/Llama-3-Taiwan-70B-Instruct-rc1", device_map="auto")
|
||||
tokenizer = llm.tokenizer
|
||||
|
||||
# Define a conversation example
|
||||
chat = [
|
||||
{"role": "system", "content": "You are an AI assistant called Twllm, created by TAME (TAiwan Mixture of Expert) project."},
|
||||
{"role": "user", "content": "你好，請問你可以完成什麼任務？"},
|
||||
{"role": "assistant", "content": "你好，我可以幫助您解決各種問題、提供資訊並協助完成多種任務。例如：回答技術問題、提供建議、翻譯文字、尋找資料或協助您安排行程等。請告訴我如何能幫助您。"},
|
||||
{"role": "user", "content": "太棒了！"}
|
||||
]
|
||||
flatten_chat_for_generation = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
|
||||
"""
|
||||
<|im_start|>user
|
||||
You are an AI assistant called Twllm, created by TAME (TAiwan Mixture of Expert) project.<|im_end|>
|
||||
<|im_start|>user
|
||||
你好，請問你可以完成什麼任務？<|im_end|>
|
||||
<|im_start|>assistant
|
||||
你好，我可以幫助您解決各種問題、提供資訊和協助您完成許多不同的任務。例如：回答技術問題、提供建議、翻譯文字、尋找資料或協助您安排行程等。請告訴我如何能幫助您。<|im_end|>
|
||||
<|im_start|>user
|
||||
太棒了！<|im_end|>
|
||||
<|im_start|>assistant
|
||||
|
||||
"""
|
||||
|
||||
# Generate a response using the custom stopping criteria
|
||||
output = llm(flatten_chat_for_generation, return_full_text=False, max_new_tokens=128, top_p=0.9, temperature=0.7, stopping_criteria=[EosListStoppingCriteria([tokenizer.eos_token_id])])
|
||||
print(output[0]['generated_text'])
|
||||
"謝謝！很高興能夠為您服務。如果有任何其他需要協助的地方，請隨時與我聯繫。我會盡最大努力為您提供所需的支援。"
|
||||
```
|
||||
|
||||
## vLLM
|
||||
|
||||
Start the server
|
||||
```bash
|
||||
export NUM_GPUS=4
|
||||
export PORT=8000
|
||||
|
||||
docker run \
|
||||
-e HF_TOKEN=$HF_TOKEN \
|
||||
--gpus '"device=0,1,2,3"' \
|
||||
-v ~/.cache/huggingface:/root/.cache/huggingface \
|
||||
-p "${PORT}:8000" \
|
||||
--ipc=host \
|
||||
vllm/vllm-openai:v0.4.0.post1 \
|
||||
--model "yentinglin/Llama-3-Taiwan-70B-Instruct-rc1" \
|
||||
-tp "${NUM_GPUS}"
|
||||
```
|
||||
|
||||
Sample client code, or you can use anything OpenAI-API compatible clients
|
||||
|
||||
```python
|
||||
# pip install "openai>=1.0.0"
|
||||
from openai import OpenAI
|
||||
# Set OpenAI's API key and API base to use vLLM's API server.
|
||||
openai_api_key = "EMPTY"
|
||||
openai_api_base = "http://localhost:8000/v1"
|
||||
|
||||
client = OpenAI(
|
||||
api_key=openai_api_key,
|
||||
base_url=openai_api_base,
|
||||
)
|
||||
|
||||
chat_response = client.chat.completions.create(
|
||||
model="yentinglin/Llama-3-Taiwan-70B-Instruct-rc1",
|
||||
messages=[
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "Tell me a joke."},
|
||||
]
|
||||
)
|
||||
print("Chat response:", chat_response)
|
||||
```
|
||||
|
||||
|
||||
Enjoy exploring the capabilities of Llama-3-Taiwan-70B! We look forward to seeing what you create with this powerful open-source model. If you have any questions or feedback, please let us know.
|
||||
|
||||
# Contributions
|
||||
- [**Professor Yun-Nung (Vivian) Chen**](https://www.csie.ntu.edu.tw/~yvchen/), for her guidance and advisement throughout the project.
|
||||
- [**Wei-Lin Chen**](mailto:wlchen@nlg.csie.ntu.edu.tw), for leading our pretraining data pipeline.
|
||||
- [**Tzu-Han Lin**](mailto:b08902126@csie.ntu.edu.tw), for synthetic data generation.
|
||||
- [**Chang-Sheng Kao**](mailto:cliff.cskao@gmail.com), for enhancing our synthetic data quality.
|
||||
- [**Kang-Chieh Chen**](mailto:b09902125@csie.ntu.edu.tw), for cleaning instruction-following data.
|
||||
- [**Min-Yi Chen**](mailto:minyi_chen@ccpgp.com) and [**Shao-Heng Hsu**](mailto:sh_hsu@ccpgp.com), for collecting chemical engineering data and benchmarks.
|
||||
- Chung-Yao Ma, Jonathan Guo and Kai-Chun Chang, for collecting manufacturing and electrical engineering data and benchmarks, and project progress management
|
||||
|
||||
# Citation
|
||||
```
|
||||
@article{DBLP:journals/corr/abs-2311-17487,
|
||||
author = {Yen{-}Ting Lin and
|
||||
Yun{-}Nung Chen},
|
||||
title = {Taiwan {LLM:} Bridging the Linguistic Divide with a Culturally Aligned
|
||||
Language Model},
|
||||
journal = {CoRR},
|
||||
volume = {abs/2311.17487},
|
||||
year = {2023},
|
||||
url = {https://doi.org/10.48550/arXiv.2311.17487},
|
||||
doi = {10.48550/ARXIV.2311.17487},
|
||||
eprinttype = {arXiv},
|
||||
eprint = {2311.17487},
|
||||
timestamp = {Tue, 05 Dec 2023 14:40:42 +0100},
|
||||
biburl = {https://dblp.org/rec/journals/corr/abs-2311-17487.bib},
|
||||
bibsource = {dblp computer science bibliography, https://dblp.org}
|
||||
}
|
||||
@article{DBLP:journals/corr/abs-2403-20180,
|
||||
author = {Po{-}Heng Chen and
|
||||
Sijia Cheng and
|
||||
Wei{-}Lin Chen and
|
||||
Yen{-}Ting Lin and
|
||||
Yun{-}Nung Chen},
|
||||
title = {Measuring Taiwanese Mandarin Language Understanding},
|
||||
journal = {CoRR},
|
||||
volume = {abs/2403.20180},
|
||||
year = {2024},
|
||||
url = {https://doi.org/10.48550/arXiv.2403.20180},
|
||||
doi = {10.48550/ARXIV.2403.20180},
|
||||
eprinttype = {arXiv},
|
||||
eprint = {2403.20180},
|
||||
timestamp = {Wed, 10 Apr 2024 17:37:45 +0200},
|
||||
biburl = {https://dblp.org/rec/journals/corr/abs-2403-20180.bib},
|
||||
bibsource = {dblp computer science bibliography, https://dblp.org}
|
||||
3
llama-3-taiwan-8B-instruct-f16.gguf
Normal file
3
llama-3-taiwan-8B-instruct-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dbc8f9ee09bb6c50ba86ee6a991f5b9e51b0d4d550c2d0670a20452c4d6b9eaf
|
||||
size 16068923744
|
||||
3
llama-3-taiwan-8B-instruct-q2_k.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q2_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9dc8dbe43270d5c36014a94a7107ea2f2f60552ca4d0503856a397b9afe83fbf
|
||||
size 3179140640
|
||||
3
llama-3-taiwan-8B-instruct-q3_k_l.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q3_k_l.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f200ce4b99307fe86f894c1873c87d5eb0e3a3478d6fcd9e62a828fcf93a0e46
|
||||
size 4321966432
|
||||
3
llama-3-taiwan-8B-instruct-q3_k_m.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q3_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c4d75f290e70aca8c7be5de8e214394eeae4f8d2e0044bd9cebd50aacac3b994
|
||||
size 4018927968
|
||||
3
llama-3-taiwan-8B-instruct-q3_k_s.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q3_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5188f1a705d29d00d1965f88fc1b7c5454633cd49e6b464a4f1756c37204bb7a
|
||||
size 3664509280
|
||||
3
llama-3-taiwan-8B-instruct-q4_0.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f387a72d2dcfd63428726fe6649794339b31f81634dc61fcdffb2d339f609ce8
|
||||
size 4661222816
|
||||
3
llama-3-taiwan-8B-instruct-q4_1.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f69b0dc1f21f65df39903a07bf43dd5c6a99013a14fafbf26247a5ec74582746
|
||||
size 5130264480
|
||||
3
llama-3-taiwan-8B-instruct-q4_k_m.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:90fd542b7996e77f73cc2c2b806f284b0ae33030a0361f68311f82d1510b4dea
|
||||
size 4920745376
|
||||
3
llama-3-taiwan-8B-instruct-q4_k_s.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q4_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2b7fed4ffe80add26a064aced339312f9cbb7f77a55e2a969e56b916e7922d62
|
||||
size 4692680096
|
||||
3
llama-3-taiwan-8B-instruct-q5_0.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7952db85324ba7ce478dabd8dc0fa061dcfd64c0a8df350cb62dbd5a79a0a304
|
||||
size 5599306144
|
||||
3
llama-3-taiwan-8B-instruct-q5_1.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6f12d612c33765d131c5753e67b584a190491dc1eca263264eed32cd8dc66f96
|
||||
size 6068347808
|
||||
3
llama-3-taiwan-8B-instruct-q5_k.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q5_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:223ab6418c2d0b36b3b34efce0984ea47df980c55c619c13cca33e26cfeda93e
|
||||
size 5732999584
|
||||
3
llama-3-taiwan-8B-instruct-q5_k_m.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q5_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:223ab6418c2d0b36b3b34efce0984ea47df980c55c619c13cca33e26cfeda93e
|
||||
size 5732999584
|
||||
3
llama-3-taiwan-8B-instruct-q5_k_s.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q5_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa75287b2f0c458cf2dec284ced8544536b5d0f298e2a5bc1ea54865ea1dc659
|
||||
size 5599306144
|
||||
3
llama-3-taiwan-8B-instruct-q6_k.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q6_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09c834b81f70039f54478cc5cb7766bfaf4c6745b667ec5d5878589d178ac80e
|
||||
size 6596019680
|
||||
3
llama-3-taiwan-8B-instruct-q8_0.gguf
Normal file
3
llama-3-taiwan-8B-instruct-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2bea3e82ff369127ceb794e2f17699d2d79d2a8c97e1a0213a62a3f2fd058908
|
||||
size 8540788064
|
||||
Reference in New Issue
Block a user