01-ai/Yi-34B
Unclaimed01.AI's Yi 34B bilingual model with strong performance in English and Chinese across diverse benchmarks.
license: apache-2.0 widget:
- example_title: "Yi-34B-Chat" text: "hi" output: text: " Hello! How can I assist you today?"
- example_title: "Yi-34B" text: "There's a place where time stands still. A place of breath taking wonder, but also" output: text: " an eerie sense that something is just not right…\nBetween the two worlds lies The Forgotten Kingdom - home to creatures long since thought extinct and ancient magic so strong it defies belief! Only here can you find what has been lost for centuries: An Elixir Of Life which will restore youth and vitality if only those who seek its power are brave enough to face up against all manner of dangers lurking in this mysterious land! But beware; some say there may even exist powerful entities beyond our comprehension whose intentions towards humanity remain unclear at best ---- they might want nothing more than destruction itself rather then anything else from their quest after immortality (and maybe someone should tell them about modern medicine)? In any event though – one thing remains true regardless : whether or not success comes easy depends entirely upon how much effort we put into conquering whatever challenges lie ahead along with having faith deep down inside ourselves too ;) So let’s get started now shall We?" pipeline_tag: text-generation
<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_dark.svg" width="200px"> <source media="(prefers-color-scheme: light)" srcset="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg" width="200px"> <img alt="specify theme context for images" src="https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg"> </picture> </br> </br> <div style="display: inline-block;"> <a href="https://github.com/01-ai/Yi/actions/workflows/build_docker_image.yml"> <img src="https://github.com/01-ai/Yi/actions/workflows/build_docker_image.yml/badge.svg"> </a> </div> <div style="display: inline-block;"> <a href="mailto:oss@01.ai"> <img src="https://img.shields.io/badge/✉️-yi@01.ai-FFE01B"> </a> </div> </div> <div align="center"> <h3 align="center">Building the Next Generation of Open-Source and Bilingual LLMs</h3> </div> <p align="center"> 🤗 <a href="https://huggingface.co/01-ai" target="_blank">Hugging Face</a> • 🤖 <a href="https://www.modelscope.cn/organization/01ai/" target="_blank">ModelScope</a> • ✡️ <a href="https://wisemodel.cn/organization/01.AI" target="_blank">WiseModel</a> </p> <p align="center"> 👩🚀 Ask questions or discuss ideas on <a href="https://github.com/01-ai/Yi/discussions" target="_blank"> GitHub </a> </p> <p align="center"> 👋 Join us on <a href="https://discord.gg/hYUwWddeAu" target="_blank"> 👾 Discord </a> or <a href="有官方的微信群嘛 · Issue #43 · 01-ai/Yi" target="_blank"> 💬 WeChat </a> </p> <p align="center"> 📝 Check out <a href="https://arxiv.org/abs/2403.04652"> Yi Tech Report </a> </p> <p align="center"> 📚 Grow at <a href="#learning-hub"> Yi Learning Hub </a> </p> <!-- DO NOT REMOVE ME --> <hr> <details open> <summary></b>📕 Table of Contents</b></summary> </details> <hr>
What is Yi?
Introduction
-
🤖 The Yi series models are the next generation of open-source large language models trained from scratch by 01.AI.
-
🙌 Targeted as a bilingual language model and trained on 3T multilingual corpus, the Yi series models become one of the strongest LLM worldwide, showing promise in language understanding, commonsense reasoning, reading comprehension, and more. For example,
-
Yi-34B-Chat model landed in second place (following GPT-4 Turbo), outperforming other LLMs (such as GPT-4, Mixtral, Claude) on the AlpacaEval Leaderboard (based on data available up to January 2024).
-
Yi-34B model ranked first among all existing open-source models (such as Falcon-180B, Llama-70B, Claude) in both English and Chinese on various benchmarks, including Hugging Face Open LLM Leaderboard (pre-trained) and C-Eval (based on data available up to November 2023).
-
🙏 (Credits to Llama) Thanks to the Transformer and Llama open-source communities, as they reduce the efforts required to build from scratch and enable the utilization of the same tools within the AI ecosystem.
-
💡 TL;DR
The Yi series models adopt the same model architecture as Llama but are NOT derivatives of Llama.
-
Both Yi and Llama are based on the Transformer structure, which has been the standard architecture for large language models since 2018.
-
Grounded in the Transformer architecture, Llama has become a new cornerstone for the majority of state-of-the-art open-source models due to its excellent stability, reliable convergence, and robust compatibility. This positions Llama as the recognized foundational framework for models including Yi.
-
Thanks to the Transformer and Llama architectures, other models can leverage their power, reducing the effort required to build from scratch and enabling the utilization of the same tools within their ecosystems.
-
However, the Yi series models are NOT derivatives of Llama, as they do not use Llama's weights.
-
As Llama's structure is employed by the majority of open-source models, the key factors of determining model performance are training datasets, training pipelines, and training infrastructure.
-
Developing in a unique and proprietary way, Yi has independently created its own high-quality training datasets, efficient training pipelines, and robust training infrastructure entirely from the ground up. This effort has led to excellent performance with Yi series models ranking just behind GPT4 and surpassing Llama on the Alpaca Leaderboard in Dec 2023.
-
News
<details> <summary>🔥 <b>2024-07-29</b>: The <a href="https://github.com/Haijian06/Yi/tree/main/Cookbook">Yi Cookbook 1.0 </a> is released, featuring tutorials and examples in both Chinese and English.</summary> </details> <details> <summary>🎯 <b>2024-05-13</b>: The <a href="https://github.com/01-ai/Yi-1.5">Yi-1.5 series models </a> are open-sourced, further improving coding, math, reasoning, and instruction-following abilities.</summary> </details> <details> <summary>🎯 <b>2024-03-16</b>: The <code>Yi-9B-200K</code> is open-sourced and available to the public.</summary> </details> <details> <summary>🎯 <b>2024-03-08</b>: <a href="https://arxiv.org/abs/2403.04652">Yi Tech Report</a> is published! </summary> </details> <details open> <summary>🔔 <b>2024-03-07</b>: The long text capability of the Yi-34B-200K has been enhanced. </summary> <br> In the "Needle-in-a-Haystack" test, the Yi-34B-200K's performance is improved by 10.5%, rising from 89.3% to an impressive 99.8%. We continue to pre-train the model on 5B tokens long-context data mixture and demonstrate a near-all-green performance. </details> <details open> <summary>🎯 <b>2024-03-06</b>: The <code>Yi-9B</code> is open-sourced and available to the public.</summary> <br> <code>Yi-9B</code> stands out as the top performer among a range of similar-sized open-source models (including Mistral-7B, SOLAR-10.7B, Gemma-7B, DeepSeek-Coder-7B-Base-v1.5 and more), particularly excelling in code, math, common-sense reasoning, and reading comprehension. </details> <details open> <summary>🎯 <b>2024-01-23</b>: The Yi-VL models, <code><a href="https://huggingface.co/01-ai/Yi-VL-34B">Yi-VL-34B</a></code> and <code><a href="https://huggingface.co/01-ai/Yi-VL-6B">Yi-VL-6B</a></code>, are open-sourced and available to the public.</summary> <br> <code><a href="https://huggingface.co/01-ai/Yi-VL-34B">Yi-VL-34B</a></code> has ranked <strong>first</strong> among all existing open-source models in the latest benchmarks, including <a href="https://arxiv.org/abs/2311.16502">MMMU</a> and <a href="https://arxiv.org/abs/2401.11944">CMMMU</a> (based on data available up to January 2024).</li> </details> <details> <summary>🎯 <b>2023-11-23</b>: <a href="#chat-models">Chat models</a> are open-sourced and available to the public.</summary> <br>This release contains two chat models based on previously released base models, two 8-bit models quantized by GPTQ, and two 4-bit models quantized by AWQ.Yi-34B-ChatYi-34B-Chat-4bitsYi-34B-Chat-8bitsYi-6B-ChatYi-6B-Chat-4bitsYi-6B-Chat-8bits
You can try some of them interactively at:
</details> <details> <summary>🔔 <b>2023-11-23</b>: The Yi Series Models Community License Agreement is updated to <a href="https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt">v2.1</a>.</summary> </details> <details> <summary>🔥 <b>2023-11-08</b>: Invited test of Yi-34B chat model.</summary> <br>Application form: </details> <details> <summary>🎯 <b>2023-11-05</b>: <a href="#base-models">The base models, </a><code>Yi-6B-200K</code> and <code>Yi-34B-200K</code>, are open-sourced and available to the public.</summary> <br>This release contains two base models with the same parameter sizes as the previous release, except that the context window is extended to 200K. </details> <details> <summary>🎯 <b>2023-11-02</b>: <a href="#base-models">The base models, </a><code>Yi-6B</code> and <code>Yi-34B</code>, are open-sourced and available to the public.</summary> <br>The first public release contains two bilingual (English/Chinese) base models with the parameter sizes of 6B and 34B. Both of them are trained with 4K sequence length and can be extended to 32K during inference time. </details> <p align="right"> [ <a href="#top">Back to top ⬆️ </a> ] </p>Models
Yi models come in multiple sizes and cater to different use cases. You can also fine-tune Yi models to meet your specific requirements.
If you want to deploy Yi models, make sure you meet the software and hardware requirements.
Chat models
| Model | Download |
|---|---|
| Yi-34B-Chat | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-34B-Chat-4bits | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-34B-Chat-8bits | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-6B-Chat | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-6B-Chat-4bits | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-6B-Chat-8bits | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
<sub><sup> - 4-bit series models are quantized by AWQ. <br> - 8-bit series models are quantized by GPTQ <br> - All quantized models have a low barrier to use since they can be deployed on consumer-grade GPUs (e.g., 3090, 4090). </sup></sub>
Base models
| Model | Download |
|---|---|
| Yi-34B | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-34B-200K | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-9B | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-9B-200K | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-6B | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
| Yi-6B-200K | • 🤗 Hugging Face • 🤖 ModelScope • 🟣 wisemodel |
<sub><sup> - 200k is roughly equivalent to 400,000 Chinese characters. <br> - If you want to use the previous version of the Yi-34B-200K (released on Nov 5, 2023), run git checkout 069cd341d60f4ce4b07ec394e82b79e94f656cf to download the weight. </sup></sub>
Model info
- For chat and base models
-
For chat models
<details style="display: inline;"><summary>For chat model limitations, see the explanations below. ⬇️</summary> <ul> <br>The released chat model has undergone exclusive training using Supervised Fine-Tuning (SFT). Compared to other standard chat models, our model produces more diverse responses, making it suitable for various downstream tasks, such as creative scenarios. Furthermore, this diversity is expected to enhance the likelihood of generating higher quality responses, which will be advantageous for subsequent Reinforcement Learning (RL) training.<br>However, this higher diversity might amplify certain existing issues, including: <li>Hallucination: This refers to the model generating factually incorrect or nonsensical information. With the model's responses being more varied, there's a higher chance of hallucination that are not based on accurate data or logical reasoning.</li> <li>Non-determinism in re-generation: When attempting to regenerate or sample responses, inconsistencies in the outcomes may occur. The increased diversity can lead to varying results even under similar input conditions.</li> <li>Cumulative Error: This occurs when errors in the model's responses compound over time. As the model generates more diverse responses, the likelihood of small inaccuracies building up into larger errors increases, especially in complex tasks like extended reasoning, mathematical problem-solving, etc.</li> <li>To achieve more coherent and consistent responses, it is advisable to adjust generation configuration parameters such as temperature, top_p, or top_k. These adjustments can help in the balance between creativity and coherence in the model's outputs.</li>
</ul> </details>
How to use Yi?
Quick start
💡 Tip: If you want to get started with the Yi model and explore different methods for inference, check out the Yi Cookbook.
Choose your path
Select one of the following paths to begin your journey with Yi!
🎯 Deploy Yi locally
If you prefer to deploy Yi models locally,
-
🙋♀️ and you have sufficient resources (for example, NVIDIA A800 80GB), you can choose one of the following methods:
-
🙋♀️ and you have limited resources (for example, a MacBook Pro), you can use llama.cpp.
🎯 Not to deploy Yi locally
If you prefer not to deploy Yi models locally, you can explore Yi's capabilities using any of the following options.
🙋♀️ Run Yi with APIs
If you want to explore more features of Yi, you can adopt one of these methods:
-
Yi APIs (Yi official)
- Early access has been granted to some applicants. Stay tuned for the next round of access!
-
Yi APIs (Replicate)
🙋♀️ Run Yi in playground
If you want to chat with Yi with more customizable options (e.g., system prompt, temperature, repetition penalty, etc.), you can try one of the following options:
-
Yi-34B-Chat-Playground (Yi official)
-
Yi-34B-Chat-Playground (Replicate)
🙋♀️ Chat with Yi
If you want to chat with Yi, you can use one of these online services, which offer a similar user experience:
-
Yi-34B-Chat (Yi official on Hugging Face)
- No registration is required.
-
Yi-34B-Chat (Yi official beta)
Quick start - pip
This tutorial guides you through every step of running Yi-34B-Chat locally on an A800 (80G) and then performing inference.
Step 0: Prerequisites
-
Make sure Python 3.10 or a later version is installed.
-
If you want to run other Yi models, see software and hardware requirements.
Step 1: Prepare your environment
To set up the environment and install the required packages, execute the following command.
git clone https://github.com/01-ai/Yi.git
cd yi
pip install -r requirements.txt
Step 2: Download the Yi model
You can download the weights and tokenizer of Yi models from the following sources:
Step 3: Perform inference
You can perform inference with Yi chat or base models as below.
Perform inference with Yi chat model
-
Create a file named
quick_start.pyand copy the following content to it.from transformers import AutoModelForCausalLM, AutoTokenizer model_path = '<your-model-path>' tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) # Since transformers 4.35.0, the GPT-Q/AWQ model can be loaded using AutoModelForCausalLM. model = AutoModelForCausalLM.from_pretrained( model_path, device_map="auto", torch_dtype='auto' ).eval() # Prompt content: "hi" messages = [ {"role": "user", "content": "hi"} ] input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') output_ids = model.generate(input_ids.to('cuda')) response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) # Model response: "Hello! How can I assist you today?" print(response) -
Run
quick_start.py.python quick_start.pyThen you can see an output similar to the one below. 🥳
Hello! How can I assist you today?
Perform inference with Yi base model
-
Yi-34B
The steps are similar to pip - Perform inference with Yi chat model.
You can use the existing file
text_generation.py.python demo/text_generation.py --model <your-model-path>Then you can see an output similar to the one below. 🥳
<details> <summary>Output. ⬇️ </summary> <br>Prompt: Let me tell you an interesting story about cat Tom and mouse Jerry,
Generation: Let me tell you an interesting story about cat Tom and mouse Jerry, which happened in my childhood. My father had a big house with two cats living inside it to kill mice. One day when I was playing at home alone, I found one of the tomcats lying on his back near our kitchen door, looking very much like he wanted something from us but couldn’t get up because there were too many people around him! He kept trying for several minutes before finally giving up...
</details> -
Yi-9B
Input
from transformers import AutoModelForCausalLM, AutoTokenizer MODEL_DIR = "01-ai/Yi-9B" model = AutoModelForCausalLM.from_pretrained(MODEL_DIR, torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR, use_fast=False) input_text = "# write the quick sort algorithm" inputs = tokenizer(input_text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_length=256) print(tokenizer.decode(outputs[0], skip_special_tokens=True))Output
# write the quick sort algorithm def quick_sort(arr): if len(arr) <= 1: return arr pivot = arr[len(arr) // 2] left = [x for x in arr if x < pivot] middle = [x for x in arr if x == pivot] right = [x for x in arr if x > pivot] return quick_sort(left) + middle + quick_sort(right) # test the quick sort algorithm print(quick_sort([3, 6, 8, 10, 1, 2, 1]))
Quick start - Docker
<details> <summary> Run Yi-34B-chat locally with Docker: a step-by-step guide. ⬇️</summary> <br>This tutorial guides you through every step of running <strong>Yi-34B-Chat on an A800 GPU</strong> or <strong>4*4090</strong> locally and then performing inference. <h4>Step 0: Prerequisites</h4> <p>Make sure you've installed <a href="https://docs.docker.com/engine/install/?open_in_browser=true">Docker</a> and <a href="https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html">nvidia-container-toolkit</a>.</p> <h4> Step 1: Start Docker </h4> <pre><code>docker run -it --gpus all \ -v <your-model-path>: /models ghcr.io/01-ai/yi:latest </code></pre> <p>Alternatively, you can pull the Yi Docker image from <code>registry.lingyiwanwu.com/ci/01-ai/yi:latest</code>.</p> <h4>Step 2: Perform inference</h4> <p>You can perform inference with Yi chat or base models as below.</p> <h5>Perform inference with Yi chat model</h5> <p>The steps are similar to <a href="#perform-inference-with-yi-chat-model">pip - Perform inference with Yi chat model</a>.</p> <p><strong>Note</strong> that the only difference is to set <code>model_path = '<your-model-mount-path>'</code> instead of <code>model_path = '<your-model-path>'</code>.</p> <h5>Perform inference with Yi base model</h5> <p>The steps are similar to <a href="#perform-inference-with-yi-base-model">pip - Perform inference with Yi base model</a>.</p> <p><strong>Note</strong> that the only difference is to set <code>--model <your-model-mount-path>'</code> instead of <code>model <your-model-path></code>.</p> </details>Quick start - conda-lock
<details> <summary>You can use <code><a href="https://github.com/conda/conda-lock">conda-lock</a></code> to generate fully reproducible lock files for conda environments. ⬇️</summary> <br> You can refer to <a href="https://github.com/01-ai/Yi/blob/ebba23451d780f35e74a780987ad377553134f68/conda-lock.yml">conda-lock.yml</a> for the exact versions of the dependencies. Additionally, you can utilize <code><a href="https://mamba.readthedocs.io/en/latest/user_guide/micromamba.html">micromamba</a></code> for installing these dependencies. <br> To install the dependencies, follow these steps:-
Install micromamba by following the instructions available <a href="https://mamba.readthedocs.io/en/latest/installation/micromamba-installation.html">here</a>.
-
Execute <code>micromamba install -y -n yi -f conda-lock.yml</code> to create a conda environment named <code>yi</code> and install the necessary dependencies.
Quick start - llama.cpp
<a href="https://github.com/01-ai/Yi/blob/main/docs/README_llama.cpp.md">The following tutorial </a> will guide you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.
<details> <summary> Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide. ⬇️</summary> <br><a href="https://github.com/01-ai/Yi/blob/main/docs/README_llama.cpp.md">This tutorial</a> guides you through every step of running a quantized model (<a href="https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main">Yi-chat-6B-2bits</a>) locally and then performing inference.</p>- Step 0: Prerequisites
- Step 1: Download llama.cpp
- Step 2: Download Yi model
- Step 3: Perform inference
Step 0: Prerequisites
-
This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip.
-
Make sure
git-lfsis installed on your machine.
Step 1: Download llama.cpp
To clone the llama.cpp repository, run the following command.
git clone git@github.com:ggerganov/llama.cpp.git
Step 2: Download Yi model
2.1 To clone XeIaso/yi-chat-6B-GGUF with just pointers, run the following command.
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF
2.2 To download a quantized Yi model (yi-chat-6b.Q2_K.gguf), run the following command.
git-lfs pull --include yi-chat-6b.Q2_K.gguf
Step 3: Perform inference
To perform inference with the Yi model, you can use one of the following methods.
Method 1: Perform inference in terminal
To compile llama.cpp using 4 threads and then conduct inference, navigate to the llama.cpp directory, and run the following command.
Tips
Replace
/Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.ggufwith the actual path of your model.By default, the model operates in completion mode.
For additional output customization options (for example, system prompt, temperature, repetition penalty, etc.), run
./main -hto check detailed descriptions and usage.
make -j4 && ./main -m /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf -p "How do you feed your pet fox? Please answer this question in 6 simple steps:\nStep 1:" -n 384 -e
...
How do you feed your pet fox? Please answer this question in 6 simple steps:
Step 1: Select the appropriate food for your pet fox. You should choose high-quality, balanced prey items that are suitable for their unique dietary needs. These could include live or frozen mice, rats, pigeons, or other small mammals, as well as fresh fruits and vegetables.
Step 2: Feed your pet fox once or twice a day, depending on the species and its individual preferences. Always ensure that they have access to fresh water throughout the day.
Step 3: Provide an appropriate environment for your pet fox. Ensure it has a comfortable place to rest, plenty of space to move around, and opportunities to play and exercise.
Step 4: Socialize your pet with other animals if possible. Interactions with other creatures can help them develop social skills and prevent boredom or stress.
Step 5: Regularly check for signs of illness or discomfort in your fox. Be prepared to provide veterinary care as needed, especially for common issues such as parasites, dental health problems, or infections.
Step 6: Educate yourself about the needs of your pet fox and be aware of any potential risks or concerns that could affect their well-being. Regularly consult with a veterinarian to ensure you are providing the best care.
...
Now you have successfully asked a question to the Yi model and got an answer! 🥳
Method 2: Perform inference in web
-
To initialize a lightweight and swift chatbot, run the following command.
cd llama.cpp ./server --ctx-size 2048 --host 0.0.0.0 --n-gpu-layers 64 --model /Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.ggufThen you can get an output like this:
... llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: freq_base = 5000000.0 llama_new_context_with_model: freq_scale = 1 ggml_metal_init: allocating ggml_metal_init: found device: Apple M2 Pro ggml_metal_init: picking default device: Apple M2 Pro ggml_metal_init: ggml.metallib not found, loading from source ggml_metal_init: GGML_METAL_PATH_RESOURCES = nil ggml_metal_init: loading '/Users/yu/llama.cpp/ggml-metal.metal' ggml_metal_init: GPU name: Apple M2 Pro ggml_metal_init: GPU family: MTLGPUFamilyApple8 (1008) ggml_metal_init: hasUnifiedMemory = true ggml_metal_init: recommendedMaxWorkingSetSize = 11453.25 MB ggml_metal_init: maxTransferRate = built-in GPU ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 128.00 MiB, ( 2629.44 / 10922.67) llama_new_context_with_model: KV self size = 128.00 MiB, K (f16): 64.00 MiB, V (f16): 64.00 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 0.02 MiB, ( 2629.45 / 10922.67) llama_build_graph: non-view tensors processed: 676/676 llama_new_context_with_model: compute buffer total size = 159.19 MiB ggml_backend_metal_buffer_type_alloc_buffer: allocated buffer, size = 156.02 MiB, ( 2785.45 / 10922.67) Available slots: -> Slot 0 - max context: 2048 llama server listening at http://0.0.0.0:8080 -
To access the chatbot interface, open your web browser and enter
http://0.0.0.0:8080into the address bar.
-
Enter a question, such as "How do you feed your pet fox? Please answer this question in 6 simple steps" into the prompt window, and you will receive a corresponding answer.
Web demo
You can build a web UI demo for Yi chat models (note that Yi base models are not supported in this senario).
Step 1: Prepare your environment.
Step 2: Download the Yi model.
Step 3. To start a web service locally, run the following command.
python demo/web_demo.py -c <your-model-path>
You can access the web UI by entering the address provided in the console into your browser.
Fine-tuning
bash finetune/scripts/run_sft_Yi_6b.sh
Once finished, you can compare the finetuned model and the base model with the following command:
bash finetune/scripts/run_eval.sh
Finetune code for Yi 6B and 34B
Preparation
From Image
By default, we use a small dataset from BAAI/COIG to finetune the base model.
You can also prepare your customized dataset in the following jsonl format:
{ "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." }
And then mount them in the container to replace the default ones:
docker run -it \
-v /path/to/save/finetuned/model/:/finetuned-model \
-v /path/to/train.jsonl:/yi/finetune/data/train.json \
-v /path/to/eval.jsonl:/yi/finetune/data/eval.json \
ghcr.io/01-ai/yi:latest \
bash finetune/scripts/run_sft_Yi_6b.sh
From Local Server
Make sure you have conda. If not, use
mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm -rf ~/miniconda3/miniconda.sh
~/miniconda3/bin/conda init bash
source ~/.bashrc
Then, create a conda env:
conda create -n dev_env python=3.10 -y
conda activate dev_env
pip install torch==2.0.1 deepspeed==0.10 tensorboard transformers datasets sentencepiece accelerate ray==2.7
Hardware Setup
For the Yi-6B model, a node with 4 GPUs, each with GPU memory larger than 60GB, is recommended.
For the Yi-34B model, because the usage of the zero-offload technique consumes a lot of CPU memory, please be careful to limit the number of GPUs in the 34B finetune training. Please use CUDA_VISIBLE_DEVICES to limit the number of GPUs (as shown in scripts/run_sft_Yi_34b.sh).
A typical hardware setup for finetuning the 34B model is a node with 8 GPUs (limited to 4 in running by CUDA_VISIBLE_DEVICES=0,1,2,3), each with GPU memory larger than 80GB, and total CPU memory larger than 900GB.
Quick Start
Download a LLM-base model to MODEL_PATH (6B and 34B). A typical folder of models is like:
|-- $MODEL_PATH
| |-- config.json
| |-- pytorch_model-00001-of-00002.bin
| |-- pytorch_model-00002-of-00002.bin
| |-- pytorch_model.bin.index.json
| |-- tokenizer_config.json
| |-- tokenizer.model
| |-- ...
Download a dataset from huggingface to local storage DATA_PATH, e.g. Dahoas/rm-static.
|-- $DATA_PATH
| |-- data
| | |-- train-00000-of-00001-2a1df75c6bce91ab.parquet
| | |-- test-00000-of-00001-8c7c51afc6d45980.parquet
| |-- dataset_infos.json
| |-- README.md
finetune/yi_example_dataset has example datasets, which are modified from BAAI/COIG
|-- $DATA_PATH
|--data
|-- train.jsonl
|-- eval.jsonl
cd into the scripts folder, copy and paste the script, and run. For example:
cd finetune/scripts
bash run_sft_Yi_6b.sh
For the Yi-6B base model, setting training_debug_steps=20 and num_train_epochs=4 can output a chat model, which takes about 20 minutes.
For the Yi-34B base model, it takes a relatively long time for initialization. Please be patient.
Evaluation
cd finetune/scripts
bash run_eval.sh
Then you'll see the answer from both the base model and the finetuned model.
</ul> </details> <p align="right"> [ <a href="#top">Back to top ⬆️ </a> ] </p>Quantization
GPT-Q
python quantization/gptq/quant_autogptq.py \
--model /base_model \
--output_dir /quantized_model \
--trust_remote_code
Once finished, you can then evaluate the resulting model as follows:
python quantization/gptq/eval_quantized_model.py \
--model /quantized_model \
--trust_remote_code
GPT-Q quantization
GPT-Q is a PTQ (Post-Training Quantization) method. It saves memory and provides potential speedups while retaining the accuracy of the model.
Yi models can be GPT-Q quantized without a lot of efforts. We provide a step-by-step tutorial below.
To run GPT-Q, we will use AutoGPTQ and exllama. And the huggingface transformers has integrated optimum and auto-gptq to perform GPTQ quantization on language models.
Do Quantization
The quant_autogptq.py script is provided for you to perform GPT-Q quantization:
python quant_autogptq.py --model /base_model \
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
Run Quantized Model
You can run a quantized model using the eval_quantized_model.py:
python eval_quantized_model.py --model /quantized_model --trust_remote_code
AWQ
python quantization/awq/quant_autoawq.py \
--model /base_model \
--output_dir /quantized_model \
--trust_remote_code
Once finished, you can then evaluate the resulting model as follows:
python quantization/awq/eval_quantized_model.py \
--model /quantized_model \
--trust_remote_code
AWQ quantization
AWQ is a PTQ (Post-Training Quantization) method. It's an efficient and accurate low-bit weight quantization (INT3/4) for LLMs.
Yi models can be AWQ quantized without a lot of efforts. We provide a step-by-step tutorial below.
To run AWQ, we will use AutoAWQ.
Do Quantization
The quant_autoawq.py script is provided for you to perform AWQ quantization:
python quant_autoawq.py --model /base_model \
--output_dir /quantized_model --bits 4 --group_size 128 --trust_remote_code
Run Quantized Model
You can run a quantized model using the eval_quantized_model.py:
python eval_quantized_model.py --model /quantized_model --trust_remote_code
Deployment
If you want to deploy Yi models, make sure you meet the software and hardware requirements.
Software requirements
Before using Yi quantized models, make sure you've installed the correct software listed below.
| Model | Software |
|---|---|
| Yi 4-bit quantized models | AWQ and CUDA |
| Yi 8-bit quantized models | GPTQ and CUDA |
Hardware requirements
Before deploying Yi in your environment, make sure your hardware meets the following requirements.
Chat models
| Model | Minimum VRAM | Recommended GPU Example |
|---|---|---|
| Yi-6B-Chat | 15 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) |
| Yi-6B-Chat-4bits | 4 GB | 1 x RTX 3060 (12 GB)<br> 1 x RTX 4060 (8 GB) |
| Yi-6B-Chat-8bits | 8 GB | 1 x RTX 3070 (8 GB) <br> 1 x RTX 4060 (8 GB) |
| Yi-34B-Chat | 72 GB | 4 x RTX 4090 (24 GB)<br> 1 x A800 (80GB) |
| Yi-34B-Chat-4bits | 20 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) <br> 1 x A100 (40 GB) |
| Yi-34B-Chat-8bits | 38 GB | 2 x RTX 3090 (24 GB) <br> 2 x RTX 4090 (24 GB)<br> 1 x A800 (40 GB) |
Below are detailed minimum VRAM requirements under different batch use cases.
| Model | batch=1 | batch=4 | batch=16 | batch=32 |
|---|---|---|---|---|
| Yi-6B-Chat | 12 GB | 13 GB | 15 GB | 18 GB |
| Yi-6B-Chat-4bits | 4 GB | 5 GB | 7 GB | 10 GB |
| Yi-6B-Chat-8bits | 7 GB | 8 GB | 10 GB | 14 GB |
| Yi-34B-Chat | 65 GB | 68 GB | 76 GB | > 80 GB |
| Yi-34B-Chat-4bits | 19 GB | 20 GB | 30 GB | 40 GB |
| Yi-34B-Chat-8bits | 35 GB | 37 GB | 46 GB | 58 GB |
Base models
| Model | Minimum VRAM | Recommended GPU Example |
|---|---|---|
| Yi-6B | 15 GB | 1 x RTX 3090 (24 GB) <br> 1 x RTX 4090 (24 GB) <br> 1 x A10 (24 GB) <br> 1 x A30 (24 GB) |
| Yi-6B-200K | 50 GB | 1 x A800 (80 GB) |
| Yi-9B | 20 GB | 1 x RTX 4090 (24 GB) |
| Yi-34B | 72 GB | 4 x RTX 4090 (24 GB) <br> 1 x A800 (80 GB) |
| Yi-34B-200K | 200 GB | 4 x A800 (80 GB) |
FAQ
<details> <summary> If you have any questions while using the Yi series models, the answers provided below could serve as a helpful reference for you. ⬇️</summary> <br>💡Fine-tuning
- <strong>Base model or Chat model - which to fine-tune?</strong>
<br>The choice of pre-trained language model for fine-tuning hinges on the computational resources you have at your disposal and the particular demands of your task.
- If you are working with a substantial volume of fine-tuning data (say, over 10,000 samples), the Base model could be your go-to choice.
- On the other hand, if your fine-tuning data is not quite as extensive, opting for the Chat model might be a more fitting choice.
- It is generally advisable to fine-tune both the Base and Chat models, compare their performance, and then pick the model that best aligns with your specific requirements.
- <strong>Yi-34B versus Yi-34B-Chat for full-scale fine-tuning - what is the difference?</strong>
<br>
The key distinction between full-scale fine-tuning on
Yi-34BandYi-34B-Chatcomes down to the fine-tuning approach and outcomes.- Yi-34B-Chat employs a Special Fine-Tuning (SFT) method, resulting in responses that mirror human conversation style more closely.
- The Base model's fine-tuning is more versatile, with a relatively high performance potential.
- If you are confident in the quality of your data, fine-tuning with
Yi-34Bcould be your go-to. - If you are aiming for model-generated responses that better mimic human conversational style, or if you have doubts about your data quality,
Yi-34B-Chatmight be your best bet.
💡Quantization
- <strong>Quantized model versus original model - what is the performance gap?</strong>
- The performance variance is largely contingent on the quantization method employed and the specific use cases of these models. For instance, when it comes to models provided by the AWQ official, from a Benchmark standpoint, quantization might result in a minor performance drop of a few percentage points.
- Subjectively speaking, in situations like logical reasoning, even a 1% performance shift could impact the accuracy of the output results.
💡General
-
<strong>Where can I source fine-tuning question answering datasets?</strong>
- You can find fine-tuning question answering datasets on platforms like Hugging Face, with datasets like m-a-p/COIG-CQIA readily available.
- Additionally, Github offers fine-tuning frameworks, such as hiyouga/LLaMA-Factory, which integrates pre-made datasets.
-
<strong>What is the GPU memory requirement for fine-tuning Yi-34B FP16?</strong> <br> The GPU memory needed for fine-tuning 34B FP16 hinges on the specific fine-tuning method employed. For full parameter fine-tuning, you'll need 8 GPUs each with 80 GB; however, more economical solutions like Lora require less. For more details, check out hiyouga/LLaMA-Factory. Also, consider using BF16 instead of FP16 for fine-tuning to optimize performance.
-
<strong>Are there any third-party platforms that support chat functionality for the Yi-34b-200k model?</strong> <br> If you're looking for third-party Chats, options include fireworks.ai.
</details>
Learning hub
<details> <summary> If you want to learn Yi, you can find a wealth of helpful educational resources here. ⬇️</summary> <br>Welcome to the Yi learning hub!
Whether you're a seasoned developer or a newcomer, you can find a wealth of helpful educational resources to enhance your understanding and skills with Yi models, including insightful blog posts, comprehensive video tutorials, hands-on guides, and more.
The content you find here has been generously contributed by knowledgeable Yi experts and passionate enthusiasts. We extend our heartfelt gratitude for your invaluable contributions!
At the same time, we also warmly invite you to join our collaborative effort by contributing to Yi. If you have already made contributions to Yi, please don't hesitate to showcase your remarkable work in the table below.
With all these resources at your fingertips, you're ready to start your exciting journey with Yi. Happy learning! 🥳
Tutorials
Blog tutorials
README truncated (exceeds 50KB). View the full version at the source.
Embed Badge
Preview
Markdown
[](https://attestry.ai/models/huggingface-01-ai-yi-34b)HTML
<a href="https://attestry.ai/models/huggingface-01-ai-yi-34b"><img src="https://regseal.ai/api/v1/registry/badge/huggingface-01-ai-yi-34b" alt="RegSeal Verification Status" /></a>