Auto Sync from git://github.com/01-ai/Yi.git/commit/9ee4974c7eff6ea8f31c690e3ba3ab19e8fe21f0

README.md

@@ -86,8 +86,8 @@ pipeline_tag: text-generation
     - [Web demo](#web-demo)
   - [Fine tune](#fine-tune)
   - [Quantization](#quantization)
-  - [Deployment](https://github.com/01-ai/Yi/blob/main/docs/deployment.md)
-  - [Learning hub](https://github.com/01-ai/Yi/blob/main/docs/learning_hub.md)
+  - [Deployment](#deployment)
+  - [Learning hub](#learning-hub)
 - [🟢 Why Yi?](#-why-yi)
   - [🌎 Ecosystem](#-ecosystem)
     - [💦 Upstream](#-upstream)
@@ -99,7 +99,6 @@ pipeline_tag: text-generation
   - [📌 Benchmarks](#-benchmarks)
     - [📊 Base model performance](#-base-model-performance)
     - [📊 Chat model performance](#-chat-model-performance)
-    - [📊 Quantized chat model performance](#-quantized-chat-model-performance)
 - [🟢 Who can use Yi?](#-who-can-use-yi)
 - [🟢 Misc.](#-misc)
   - [Ackknowledgements](#acknowledgments)
@@ -121,8 +120,29 @@ pipeline_tag: text-generation
   - For English language capability, the Yi series models ranked 2nd (just behind GPT-4), outperforming other LLMs (such as LLaMA2-chat-70B, Claude 2, and ChatGPT) on the [AlpacaEval Leaderboard](https://tatsu-lab.github.io/alpaca_eval/) in Dec 2023.
   
   - For Chinese language capability, the Yi series models landed in 2nd place (following GPT-4), surpassing other LLMs (such as Baidu ERNIE, Qwen, and Baichuan) on the [SuperCLUE](https://www.superclueai.com/) in Oct 2023.
+  
+  - 🙏 (Credits to LLaMA) Thanks to the Transformer and LLaMA open-source communities, as they reducing the efforts required to build from scratch and enabling the utilization of the same tools within the AI ecosystem.  
+  <details style="display: inline;"><summary> If you're interested in Yi's adoption of LLaMA architecture and license usage policy, see  <span style="color:  green;">Yi's relation with LLaMA</span> ⬇️</summary> <ul> <br>
+> 💡 TL;DR
+> 
+> The Yi series models adopt the same model architecture as LLaMA but are **NOT** derivatives of LLaMA.
+
+- Both Yi and LLaMA are all 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](https://tatsu-lab.github.io/alpaca_eval/). 
+</ul>
+</details>
+
+
 
-- 🙏 (Credits to LLaMA) Thanks to the Transformer and LLaMA open-source communities, as they reducing the efforts required to build from scratch and enabling the utilization of the same tools within the AI ecosystem. If you're interested in Yi's adoption of LLaMA architecture and license usage policy, see [Yi's relation with LLaMA](https://github.com/01-ai/Yi/blob/main/docs/yi_relation_llama.md).
 
 <div align="right"> [ <a href="#building-the-next-generation-of-open-source-and-bilingual-llms">Back to top ⬆️ </a> ] </div>
 
@@ -130,18 +150,19 @@ pipeline_tag: text-generation
 
 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, see [software and hardware requirements](https://github.com/01-ai/Yi/blob/main/docs/deployment.md#hardware-requirements).
+If you want to deploy Yi models, see [software and hardware requirements](#deployment)
 
 ### Chat models
 
 | Model | Download  
 |---|---
-Yi-6B-Chat| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat/summary)
-Yi-6B-Chat-4bits |	• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-4bits)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-4bits/summary)
-Yi-6B-Chat-8bits	|  • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-8bits/summary)
 Yi-34B-Chat	| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat/summary)
 Yi-34B-Chat-4bits	| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-4bits)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-4bits/summary)
 Yi-34B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-Chat-8bits/summary)
+Yi-6B-Chat| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat/summary)
+Yi-6B-Chat-4bits |	• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-4bits)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-4bits/summary)
+Yi-6B-Chat-8bits	|  • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-Chat-8bits) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-Chat-8bits/summary)
+
 
 <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>
 
@@ -149,10 +170,10 @@ Yi-34B-Chat-8bits | • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-
 
 | Model | Download | 
 |---|---|
-Yi-6B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B/summary)
-Yi-6B-200K	| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-200K/summary)
 Yi-34B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B/summary)
 Yi-34B-200K|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-200K)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-34B-200K/summary)
+Yi-6B| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B)  • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B/summary)
+Yi-6B-200K	| • [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-6B-200K) • [🤖 ModelScope](https://www.modelscope.cn/models/01ai/Yi-6B-200K/summary)
 
 <sub><sup> - 200k is roughly equivalent to 400,000 Chinese characters.  </sup></sub>
 
@@ -172,7 +193,17 @@ Yi-34B-200K|• [🤗 Hugging Face](https://huggingface.co/01-ai/Yi-34B-200K)
 
 - For chat models:
   
-  - For detailed chat model limitations, see [limitations of chat model](https://github.com/01-ai/Yi/blob/main/docs/README_legacy.md#limitations-of-chat-model).
+  <details style="display: inline;"><summary>For chat model limitations, see ⬇️</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>
 
 <div align="right"> [ <a href="#building-the-next-generation-of-open-source-and-bilingual-llms">Back to top ⬆️ </a> ] </div>
 
@@ -249,7 +280,7 @@ Getting up and running with Yi models is simple with multiple choices available.
 
 Select one of the following paths to begin your journey with Yi!
 
- ![Quick start - Choose your path](./assets/img/quick_start_path.png)
+ ![Quick start - Choose your path](https://github.com/01-ai/Yi/blob/main/assets/img/quick_start_path.png)
 
 #### 🎯 Deploy Yi locally
 
@@ -260,7 +291,7 @@ If you prefer to deploy Yi models locally,
     - [Docker](https://github.com/01-ai/Yi/blob/main/docs/README_legacy.md#11-docker)
     - [conda-lock](https://github.com/01-ai/Yi/blob/main/docs/README_legacy.md#12-local-development-environment)
 
-  - 🙋‍♀️ and you have **limited** resources (for example, a MacBook Pro), you can use [llama.cpp](https://github.com/01-ai/Yi/blob/main/docs/yi_llama.cpp.md).
+  - 🙋‍♀️ and you have **limited** resources (for example, a MacBook Pro), you can use [llama.cpp](#quick-start---llamacpp)
 
 #### 🎯 Not to deploy Yi locally
 
@@ -294,7 +325,7 @@ If you want to chat with Yi with more customizable options (e.g., system prompt,
 - [Yi-34B-Chat](https://platform.lingyiwanwu.com/) (Yi official beta)
   - Access is available through a whitelist. Welcome to apply (fill out a form in [English](https://cn.mikecrm.com/l91ODJf) or [Chinese](https://cn.mikecrm.com/gnEZjiQ)).
 
-### pip
+### Quick start - pip
 
 This tutorial guides you through every step of running **Yi-34B-Chat locally on an A800 (80G)** and then performing inference.
 
@@ -302,7 +333,7 @@ This tutorial guides you through every step of running **Yi-34B-Chat locally on
  
 - Make sure Python 3.10 or later version is installed.
 
-- If you want to run other Yi models, see [software and hardware requirements](https://github.com/01-ai/Yi/blob/main/docs/deployment.md).
+- If you want to run other Yi models, see [software and hardware requirements](#deployment)
 
 #### Step 1: Prepare your environment 
 
@@ -383,7 +414,7 @@ Then you can see an output similar to the one below. 🥳
 
 <details>
 
-<summary>Output</summary>
+<summary>Output ⬇️ </summary>
 
 <br>
 
@@ -393,45 +424,167 @@ Then you can see an output similar to the one below. 🥳
 
 </details>
 
-### Docker
+### 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> 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 &lt;your-model-path&gt;: /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 = '&lt;your-model-mount-path&gt;'</code> instead of <code>model_path = '&lt;your-model-path&gt;'</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 &lt;your-model-mount-path&gt;'</code> instead of <code>model &lt;your-model-path&gt;</code>.</p>
+</details>
+
 
-This tutorial guides you through every step of running **Yi-34B-Chat on an A800 GPU** locally and then performing inference.
 
-#### Step 0: Prerequistes
+### Quick start - llama.cpp
+<details>
+<summary> Run Yi-chat-6B-2bits locally with llama.cpp: a step-by-step guide ⬇️</summary> 
+<br>This tutorial 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>
 
-- Make sure you've installed [Docker](https://docs.docker.com/engine/install/?open_in_browser=true) and [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html).
+- [Step 0: Prerequisites](#step-0-prerequisites)
+- [Step 1: Download llama.cpp](#step-1-download-llamacpp)
+- [Step 2: Download Yi model](#step-2-download-yi-model)
+- [Step 3: Perform inference](#step-3-perform-inference)
 
-#### Step 1: Start Docker
+#### Step 0: Prerequisites 
+
+- This tutorial assumes you use a MacBook Pro with 16GB of memory and an Apple M2 Pro chip.
+  
+- Make sure [`git-lfs`](https://git-lfs.com/) is installed on your machine.
+  
+#### Step 1: Download `llama.cpp`
+
+To clone the [`llama.cpp`](https://github.com/ggerganov/llama.cpp) repository, run the following command.
 
 ```bash
-docker run -it --gpus all \
-    -v <your-model-path>: /models
-    ghcr.io/01-ai/yi:latest 
+git clone git@github.com:ggerganov/llama.cpp.git
 ```
 
-Alternatively, you can pull the Yi Docker image from `registry.lingyiwanwu.com/ci/01-ai/yi:latest`.
+#### Step 2: Download Yi model
 
-#### Step 2: Perform inference
+2.1 To clone [XeIaso/yi-chat-6B-GGUF](https://huggingface.co/XeIaso/yi-chat-6B-GGUF/tree/main) with just pointers, run the following command.
 
-You can perform inference with Yi chat or base models as below.
-   
-##### Perform inference with Yi chat model
+```bash
+GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/XeIaso/yi-chat-6B-GGUF
+```
 
-The steps are similar to [pip - Perform inference with Yi chat model](#perform-inference-with-yi-chat-model).
+2.2 To download a quantized Yi model ([yi-chat-6b.Q2_K.gguf](https://huggingface.co/XeIaso/yi-chat-6B-GGUF/blob/main/yi-chat-6b.Q2_K.gguf)), run the following command.
+
+```bash
+git-lfs pull --include yi-chat-6b.Q2_K.gguf
+```
 
-**Note** that the only difference is to set `model_path = '<your-model-mount-path>'` instead of `model_path = '<your-model-path>'`.
+#### Step 3: Perform inference
 
-##### Perform inference with Yi base model
+To perform inference with the Yi model, you can use one of the following methods.
 
-The steps are similar to [pip - Perform inference with Yi base model](#perform-inference-with-yi-base-model).
+- [Method 1: Perform inference in terminal](#method-1-perform-inference-in-terminal)
+  
+- [Method 2: Perform inference in web](#method-2-perform-inference-in-web)
+
+##### Method 1: Perform inference in terminal
 
-**Note** that the only difference is to set `--model <your-model-mount-path>'` instead of  `model <your-model-path>`.
+To compile `llama.cpp` using 4 threads and then conduct inference, navigate to the `llama.cpp` directory, and run the following command.
 
-### Run Yi with llama.cpp
+> ##### Tips
+> 
+> - Replace `/Users/yu/yi-chat-6B-GGUF/yi-chat-6b.Q2_K.gguf` with 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 -h` to check detailed descriptions and usage.
 
-If you have limited resources, you can try [llama.cpp](https://github.com/ggerganov/llama.cpp) or [ollama.cpp](https://ollama.ai/) (especially for Chinese users) to run Yi models in a few minutes locally.
+```bash
+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
 
-For a step-by-step tutorial, see [Run Yi with llama.cpp](https://github.com/01-ai/Yi/edit/main/docs/yi_llama.cpp.md).
+...
+
+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
+
+1. To initialize a lightweight and swift chatbot, navigate to the `llama.cpp` directory, and run the following command.
+
+    ```bash
+    ./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.gguf
+    ```
+
+    Then you can get an output like this:
+
+
+    ```bash
+    ...
+
+    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
+    ```
+
+2. To access the chatbot interface, open your web browser and enter `http://0.0.0.0:8080` into the address bar. 
+   
+    ![Yi model chatbot interface - llama.cpp](https://github.com/01-ai/Yi/blob/main/assets/img/yi_llama_cpp1.png)
+
+
+3. 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.
+
+    ![Ask a question to Yi model - llama.cpp](https://github.com/01-ai/Yi/blob/main/assets/img/yi_llama_cpp2.png)
+
+</ul>
+</details>
 
 ### Web demo
 
@@ -462,8 +615,119 @@ Once finished, you can compare the finetuned model and the base model with the f
 ```bash
 bash finetune/scripts/run_eval.sh
 ```
+<details style="display: inline;"><summary>For advanced usage (like fine-tuning based on your custom data), see ⬇️</summary> <ul>
+
+### Finetune code for Yi 6B and 34B
+
+#### Preparation
+
+##### From Image
+
+By default, we use a small dataset from [BAAI/COIG](https://huggingface.co/datasets/BAAI/COIG) to finetune the base model.
+You can also prepare your customized dataset in the following `jsonl` format:
+
+```json
+{ "prompt": "Human: Who are you? Assistant:", "chosen": "I'm Yi." }
+```
+
+And then mount them in the container to replace the default ones:
+
+```bash
+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
+
+```bash
+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:
+
+```bash
+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 has GPU mem larger than 60GB is recommended.
+
+For the Yi-34B model, because the usage of zero-offload technique takes a lot CPU memory, please be careful to limit the GPU numbers in 34B finetune training. Please use CUDA_VISIBLE_DEVICES to limit the GPU number (as shown in scripts/run_sft_Yi_34b.sh).
+
+A typical hardware setup for finetuning 34B model is a node with 8GPUS (limit to 4 in running by CUDA_VISIBLE_DEVICES=0,1,2,3), each has GPU mem larger than 80GB, with total CPU mem larger than 900GB.
+
+#### Quick Start
+
+Download a LLM-base model to MODEL_PATH (6B and 34B). A typical folder of models is like:
+
+```bash
+|-- $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.
+
+```bash
+|-- $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](https://huggingface.co/datasets/BAAI/COIG)
+
+```bash
+|-- $DATA_PATH
+    |--data
+        |-- train.jsonl
+        |-- eval.jsonl
+```
+
+`cd` into the scripts folder, copy and paste the script, and run. For example:
+
+```bash
+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
+
+```bash
+cd finetune/scripts
+
+bash run_eval.sh
+```
 
-For advanced usage (like fine-tuning based on your custom data), see [fine-tune code for Yi 6B and 34B](https://github.com/01-ai/Yi/tree/main/finetune).
+Then you'll see the answer from both the base model and the finetuned model
+</ul>
+</details>
 
 ### Quantization
 
@@ -483,7 +747,41 @@ python quantization/gptq/eval_quantized_model.py \
   --trust_remote_code
 ```
 
-For a more detailed explanation, please read the [doc](https://github.com/01-ai/Yi/tree/main/quantization/gptq)
+<details style="display: inline;"><summary>For a more detailed explanation, see ⬇️</summary> <ul>
+
+#### GPT-Q quantization
+
+[GPT-Q](https://github.com/IST-DASLab/gptq) is a PTQ(Post-Training Quantization)
+method. It's memory saving 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](https://github.com/PanQiWei/AutoGPTQ) and
+[exllama](https://github.com/turboderp/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:
+
+```bash
+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`:
+
+```bash
+python eval_quantized_model.py --model /quantized_model --trust_remote_code
+```
+</ul>
+</details>
 
 #### AWQ
 ```bash
@@ -500,11 +798,118 @@ python quantization/awq/eval_quantized_model.py \
   --model /quantized_model                       \
   --trust_remote_code
 ```
+<details style="display: inline;"><summary>For detailed explanations, see ⬇️</summary> <ul>
 
-For detailed explanations, see [AWQ quantization](https://github.com/01-ai/Yi/tree/main/quantization/awq).
+#### AWQ quantization
 
+[AWQ](https://github.com/mit-han-lab/llm-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](https://github.com/casper-hansen/AutoAWQ).
+
+##### Do Quantization
+
+The `quant_autoawq.py` script is provided for you to perform AWQ quantization:
+
+```bash
+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`:
+
+```bash
+python eval_quantized_model.py --model /quantized_model --trust_remote_code
+```
+
+
+</ul>
+</details>
 <div align="right"> [ <a href="#building-the-next-generation-of-open-source-and-bilingual-llms">Back to top ⬆️ </a> ] </div>
 
+### Deployment
+<details>
+<summary> Software and hardware requirements of deploying Yi models ⬇️</summary> 
+
+#### 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](https://github.com/casper-hansen/AutoAWQ?tab=readme-ov-file#install-from-pypi)
+Yi 8-bit quantized models |  [GPTQ and CUDA](https://github.com/PanQiWei/AutoGPTQ?tab=readme-ov-file#quick-installation)
+
+
+#### 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         | RTX 3090 <br> RTX 4090 <br>  A10 <br> A30             |
+| Yi-6B-Chat-4bits     | 4 GB          | RTX 3060 <br>  RTX 4060                     |
+| Yi-6B-Chat-8bits     | 8 GB          | RTX 3070 <br> RTX 4060                     |
+| Yi-34B-Chat          | 72 GB         | 4 x RTX 4090 <br> A800 (80GB)               |
+| Yi-34B-Chat-4bits    | 20 GB         | RTX 3090  <br> RTX 4090 <br> A10 <br> A30 <br> A100 (40GB) |
+| Yi-34B-Chat-8bits    | 38 GB         | 2 x RTX 3090  <br> 2 x RTX 4090 <br> A800  (40GB) |
+
+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         | RTX3090 <br> RTX4090 <br> A10 <br> A30               |
+| Yi-6B-200K           | 50 GB         | A800 (80 GB)                            |
+| Yi-34B               | 72 GB         | 4 x RTX 4090 <br> A800 (80 GB)               |
+| Yi-34B-200K          | 200 GB        | 4 x A800 (80 GB)                        |
+
+</details>
+
+### Learning hub
+<details>
+<summary> Learning materials of Yi ⬇️</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
+
+| Type        | Deliverable                                            |      Date      |     Author     |
+|-------------|--------------------------------------------------------|----------------|----------------|
+| Blog        | [本地运行零一万物 34B 大模型，使用 Llama.cpp & 21G 显存](https://zhuanlan.zhihu.com/p/668921042)                  |  2023-11-26  |  [苏洋](https://github.com/soulteary)  |
+| Blog        | [Running Yi-34B-Chat locally using LlamaEdge](https://www.secondstate.io/articles/yi-34b/)                   |  2023-11-30  |  [Second State](https://github.com/second-state)  |
+| Blog        | [零一万物模型折腾笔记：官方 Yi-34B 模型基础使用](https://zhuanlan.zhihu.com/p/671387298)                           | 2023-12-10 |  [苏洋](https://github.com/soulteary)  |
+| Blog        | [CPU 混合推理，非常见大模型量化方案：“二三五六” 位量化方案](https://zhuanlan.zhihu.com/p/671698216)                  | 2023-12-12 |  [苏洋](https://github.com/soulteary)  |
+| Video       | [只需 24G 显存，用 vllm 跑起来 Yi-34B 中英双语大模型](https://www.bilibili.com/video/BV17t4y1f7Ee/)               | 2023-12-28 |  漆妮妮  |
+| Video       | [Install Yi 34B Locally - Chinese English Bilingual LLM](https://www.youtube.com/watch?v=CVQvj4Wrh4w&t=476s) | 2023-11-05  |  Fahd Mirza  |
+</details>
+
+
 # 🟢 Why Yi? 
 
   - [🌎 Ecosystem](#-ecosystem)
@@ -515,9 +920,8 @@ For detailed explanations, see [AWQ quantization](https://github.com/01-ai/Yi/tr
       - [🛠️ Fine-tuning](#️-fine-tuning)
       - [API](#api)
   - [📌 Benchmarks](#-benchmarks)
-    - [📊 Base model performance](#-base-model-performance)
     - [📊 Chat model performance](#-chat-model-performance)
-    - [📊 Quantized chat model performance](#-quantized-chat-model-performance)
+    - [📊 Base model performance](#-base-model-performance)
  
 ## 🌎 Ecosystem
 
@@ -600,76 +1004,46 @@ If you're seeking to explore the diverse capabilities within Yi's thriving famil
 
 ## 📌 Benchmarks 
 
-- [📊 Base model performance](#-base-model-performance)
 - [📊 Chat model performance](#-chat-model-performance)
-- [📊 Quantized chat model performance](#-quantized-chat-model-performance)
+- [📊 Base model performance](#-base-model-performance)
 
-### 📊 Base model performance
+### 📊 Chat model performance
+🎯 Performance evaluation
+- Yi-34B-chat stands out, doing better than most big models in almost all tests. 
+- Both Yi-34B-chat and its variant, Yi-34B-Chat-8bits (GPTQ), take the top spots in tests including MMLU, CMMLU, BBH, and GSM8k.
 
-| Model         |   MMLU   |  CMMLU   |  C-Eval  |  GAOKAO  |   BBH    | Common-sense Reasoning | Reading Comprehension | Math & Code |
-| :------------ | :------: | :------: | :------: | :------: | :------: | :--------------------: | :-------------------: | :---------: |
-|               |  5-shot  |  5-shot  |  5-shot  |  0-shot  | 3-shot@1 |           -            |           -           |      -      |
-| LLaMA2-34B    |   62.6   |    -     |    -     |    -     |   44.1   |          69.9          |         68.0          |    26.0     |
-| LLaMA2-70B    |   68.9   |   53.3   |    -     |   49.8   |   51.2   |          71.9          |         69.4          |    36.8     |
-| Baichuan2-13B |   59.2   |   62.0   |   58.1   |   54.3   |   48.8   |          64.3          |         62.4          |    23.0     |
-| Qwen-14B      |   66.3   |   71.0   |   72.1   |   62.5   |   53.4   |          73.3          |         72.5          |  **39.8**   |
-| Skywork-13B   |   62.1   |   61.8   |   60.6   |   68.1   |   41.7   |          72.4          |         61.4          |    24.9     |
-| InternLM-20B  |   62.1   |   59.0   |   58.8   |   45.5   |   52.5   |          78.3          |           -           |    30.4     |
-| Aquila-34B    |   67.8   |   71.4   |   63.1   |    -     |    -     |           -            |           -           |      -      |
-| Falcon-180B   |   70.4   |   58.0   |   57.8   |   59.0   |   54.0   |          77.3          |         68.8          |    34.0     |
-| Yi-6B         |   63.2   |   75.5   |   72.0   |   72.2   |   42.8   |          72.3          |         68.7          |    19.8     |
-| Yi-6B-200K    |   64.0   |   75.3   |   73.5   |   73.9   |   42.0   |          72.0          |         69.1          |    19.0     |
-| **Yi-34B**    | **76.3** | **83.7** |   81.4   |   82.8   | **54.3** |        **80.1**        |         76.4          |    37.1     |
-| Yi-34B-200K   |   76.1   |   83.6   | **81.9** | **83.4** |   52.7   |          79.7          |       **76.6**        |    36.3     |
-
-While benchmarking open-source models, we have observed a disparity between the
-results generated by our pipeline and those reported in public sources (e.g.
-OpenCompass). Upon conducting a more in-depth investigation of this difference,
-we have discovered that various models may employ different prompts,
-post-processing strategies, and sampling techniques, potentially resulting in
-significant variations in the outcomes. Our prompt and post-processing strategy
-remains consistent with the original benchmark, and greedy decoding is employed
-during evaluation without any post-processing for the generated content. For
-scores that were not reported by the original authors (including scores reported
-with different settings), we try to get results with our pipeline.
-
-To evaluate the model's capability extensively, we adopted the methodology
-outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande,
-ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ
-were incorporated to evaluate reading comprehension. CSQA was exclusively tested
-using a 7-shot setup, while all other tests were conducted with a 0-shot
-configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1),
-HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due
-to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score
-is derived by averaging the scores on the remaining tasks. Since the scores for
-these two tasks are generally lower than the average, we believe that
-Falcon-180B's performance was not underestimated.
+![Chat model performance](./assets/img/benchmark_chat.png) 
 
-### 📊 Chat model performance
+<details>
+<summary>🎯 Evaluation methods and challenges ⬇️ </summary>
 
-| Model                   | MMLU      | MMLU      | CMMLU     | CMMLU     | C-Eval(val)<sup>*</sup> | C-Eval(val)<sup>*</sup> | Truthful QA | BBH       | BBH       | GSM8k     | GSM8k     |
-| ----------------------- | --------- | --------- | --------- | --------- | ----------------------- | ----------------------- | ----------- | --------- | --------- | --------- | --------- |
-|                         | 0-shot    | 5-shot    | 0-shot    | 5-shot    | 0-shot                  | 5-shot                  | 0-shot      | 0-shot    | 3-shot    | 0-shot    | 4-shot    |
-| LLaMA2-13B-Chat         | 50.88     | 47.33     | 27.47     | 35.08     | 27.93                   | 35.88                   | 36.84       | 32.90     | 58.22     | 36.85     | 2.73      |
-| LLaMA2-70B-Chat         | 59.42     | 59.86     | 36.10     | 40.99     | 34.99                   | 41.31                   | 53.95       | 42.36     | 58.53     | 47.08     | 58.68     |
-| Baichuan2-13B-Chat      | 55.09     | 50.14     | 58.64     | 59.47     | 56.02                   | 54.75                   | 48.98       | 38.81     | 47.15     | 45.72     | 23.28     |
-| Qwen-14B-Chat           | 63.99     | 64.98     | 67.73     | 70.57     | 66.12                   | 70.06                   | 52.49       | 49.65     | 54.98     | 59.51     | 61.18     |
-| InternLM-Chat-20B       | 55.55     | 57.42     | 53.55     | 53.75     | 51.19                   | 53.57                   | 51.75       | 42.41     | 36.68     | 15.69     | 43.44     |
-| AquilaChat2-34B v1.2    | 65.15     | 66.70     | 67.51     | 70.02     | **82.99**               | **89.38**               | **64.33**   | 20.12     | 34.28     | 11.52     | 48.45     |
-| Yi-6B-Chat              | 58.24     | 60.99     | 69.44     | 74.71     | 68.80                   | 74.22                   | 50.58       | 39.70     | 47.15     | 38.44     | 44.88     |
-| Yi-6B-Chat-8bits(GPTQ)  | 58.29     | 60.96     | 69.21     | 74.69     | 69.17                   | 73.85                   | 49.85       | 40.35     | 47.26     | 39.42     | 44.88     |
-| Yi-6B-Chat-4bits(AWQ)   | 56.78     | 59.89     | 67.70     | 73.29     | 67.53                   | 72.29                   | 50.29       | 37.74     | 43.62     | 35.71     | 38.36     |
-| Yi-34B-Chat             | **67.62** | 73.46     | **79.11** | **81.34** | 77.04                   | 78.53                   | 62.43       | 51.41     | **71.74** | **71.65** | **75.97** |
-| Yi-34B-Chat-8bits(GPTQ) | 66.24     | **73.69** | 79.05     | 81.23     | 76.82                   | 78.97                   | 61.84       | **52.08** | 70.97     | 70.74     | 75.74     |
-| Yi-34B-Chat-4bits(AWQ)  | 65.77     | 72.42     | 78.21     | 80.50     | 75.71                   | 77.27                   | 61.84       | 48.30     | 69.39     | 70.51     | 74.00     |
-
-We evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA. Generally, the zero-shot approach is more common in chat models. Our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text. Some models are not well-suited to produce output in the specific format required by instructions in a few datasets, which leads to suboptimal results. 
+- **Evaluation methods**: we evaluated various benchmarks using both zero-shot and few-shot methods, except for TruthfulQA.
+- **Zero-shot vs. few-shot**: in chat models, the zero-shot approach is more commonly employed.
+- **Evaluation strategy**: our evaluation strategy involves generating responses while following instructions explicitly or implicitly (such as using few-shot examples). We then isolate relevant answers from the generated text.
+- **Challenges faced**: some models are not well-suited to produce output in the specific format required by instructions in few datasets, which leads to suboptimal results.
 
 <strong>*</strong>: C-Eval results are evaluated on the validation datasets
+</details>
+
+### 📊 Base model performance
+🎯 Performance evaluation
+- Yi-34B stands out as the top performer among the big models, beating others like LLaMA2-70B and Falcon-180B in most tests.
+- Yi-34B ranks first in MMLU, CMMLU, BBH, and common-sense reasoning.
+- Yi-34B-200K ranks first C-Eval, GAOKAO, and reading comprehension.
 
-### 📊 Quantized chat model performance
+![Base model performance](./assets/img/benchmark_base.png)
 
-We also provide both 4-bit (AWQ) and 8-bit (GPTQ) quantized Yi chat models. Evaluation results on various benchmarks have shown that the quantized models have **negligible** losses. Additionally, they reduce the memory footprint size. 
+<details>
+<summary>🎯 Evaluation methods ⬇️</summary>
+
+- **Disparity in Results**: while benchmarking open-source models, a disparity has been noted between results from our pipeline and those reported by public sources like OpenCompass.
+- **Investigation Findings**: a deeper investigation reveals that variations in prompts, post-processing strategies, and sampling techniques across models may lead to significant outcome differences.
+- **Uniform Benchmarking Process**: our methodology aligns with the original benchmarks—consistent prompts and post-processing strategies are used, and greedy decoding is applied during evaluations without any post-processing for the generated content.
+- **Efforts to Retrieve Unreported Scores**: for scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline.
+- **Extensive Model Evaluation**: to evaluate the model’s capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension.
+- **Special Configurations**: CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code".
+- **Falcon-180B Caveat**: Falcon-180B was not tested on QuAC and OBQA due to technical constraints. Its performance score is an average from other tasks, and considering the generally lower scores of these two tasks, Falcon-180B's capabilities are likely not underestimated.
+</details>
 
 # 🟢 Who can use Yi?
 
@@ -741,9 +1115,7 @@ as well as any associated data security concerns.
 ### 🪪 License
 
 The source code in this repo is licensed under the [Apache 2.0
-license](https://github.com/01-ai/Yi/blob/main/LICENSE). The Yi series models
-are fully open for academic research and free commercial usage with permission
-via applications. All usage must adhere to the [Yi Series Models Community License Agreement 2.1](https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt).
+license](https://github.com/01-ai/Yi/blob/main/LICENSE). The Yi series models are fully open for academic research and free for commercial use, with automatic permission granted upon application. All usage must adhere to the [Yi Series Models Community License Agreement 2.1](https://github.com/01-ai/Yi/blob/main/MODEL_LICENSE_AGREEMENT.txt).
 For free commercial use, you only need to send an email to [get official commercial permission](https://www.lingyiwanwu.com/yi-license).
 
 <div align="right"> [ <a href="#building-the-next-generation-of-open-source-and-bilingual-llms">Back to top ⬆️ </a> ] </div>