Upload README.md

README.md

@@ -0,0 +1,478 @@
+---
+base_model: Xwin-LM/Xwin-LM-7B-V0.2
+inference: false
+license: llama2
+model_creator: Xwin-LM
+model_name: Xwin LM 7B v0.2
+model_type: llama
+prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
+  The assistant gives helpful, detailed, and polite answers to the user''s questions.
+  USER: {prompt} ASSISTANT:
+
+  '
+quantized_by: TheBloke
+---
+<!-- markdownlint-disable MD041 -->
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
+    </div>
+    <div style="display: flex; flex-direction: column; align-items: flex-end;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
+    </div>
+</div>
+<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Xwin LM 7B v0.2 - AWQ
+- Model creator: [Xwin-LM](https://huggingface.co/Xwin-LM)
+- Original model: [Xwin LM 7B v0.2](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2)
+
+<!-- description start -->
+## Description
+
+This repo contains AWQ model files for [Xwin-LM's Xwin LM 7B v0.2](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2).
+
+
+### About AWQ
+
+AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
+
+It is supported by:
+
+- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
+- [vLLM](https://github.com/vllm-project/vllm) - Llama and Mistral models only
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
+
+<!-- description end -->
+<!-- repositories-available start -->
+## Repositories available
+
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Xwin-LM-7B-V0.2-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Xwin-LM-7B-V0.2-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Xwin-LM-7B-V0.2-GGUF)
+* [Xwin-LM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2)
+<!-- repositories-available end -->
+
+<!-- prompt-template start -->
+## Prompt template: Vicuna
+
+```
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+
+```
+
+<!-- prompt-template end -->
+
+
+<!-- README_AWQ.md-provided-files start -->
+## Provided files, and AWQ parameters
+
+For my first release of AWQ models, I am releasing 128g models only. I will consider adding 32g as well if there is interest, and once I have done perplexity and evaluation comparisons, but at this time 32g models are still not fully tested with AutoAWQ and vLLM.
+
+Models are released as sharded safetensors files.
+
+| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
+| ------ | ---- | -- | ----------- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/Xwin-LM-7B-V0.2-AWQ/tree/main) | 4 | 128 | [wikitext](https://huggingface.co/datasets/wikitext/viewer/wikitext-2-v1/test) | 4096 | 3.89 GB
+
+<!-- README_AWQ.md-provided-files end -->
+
+<!-- README_AWQ.md-text-generation-webui start -->
+## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
+
+Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
+
+It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
+
+1. Click the **Model tab**.
+2. Under **Download custom model or LoRA**, enter `TheBloke/Xwin-LM-7B-V0.2-AWQ`.
+3. Click **Download**.
+4. The model will start downloading. Once it's finished it will say "Done".
+5. In the top left, click the refresh icon next to **Model**.
+6. In the **Model** dropdown, choose the model you just downloaded: `Xwin-LM-7B-V0.2-AWQ`
+7. Select **Loader: AutoAWQ**.
+8. Click Load, and the model will load and is now ready for use.
+9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
+10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
+<!-- README_AWQ.md-text-generation-webui end -->
+
+<!-- README_AWQ.md-use-from-vllm start -->
+## Multi-user inference server: vLLM
+
+Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
+
+- Please ensure you are using vLLM version 0.2 or later.
+- When using vLLM as a server, pass the `--quantization awq` parameter.
+
+For example:
+
+```shell
+python3 python -m vllm.entrypoints.api_server --model TheBloke/Xwin-LM-7B-V0.2-AWQ --quantization awq
+```
+
+- When using vLLM from Python code, again set `quantization=awq`.
+
+For example:
+
+```python
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Tell me about AI",
+    "Write a story about llamas",
+    "What is 291 - 150?",
+    "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
+]
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+'''
+
+prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
+
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+llm = LLM(model="TheBloke/Xwin-LM-7B-V0.2-AWQ", quantization="awq", dtype="auto")
+
+outputs = llm.generate(prompts, sampling_params)
+
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+```
+<!-- README_AWQ.md-use-from-vllm start -->
+
+<!-- README_AWQ.md-use-from-tgi start -->
+## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
+
+Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
+
+Example Docker parameters:
+
+```shell
+--model-id TheBloke/Xwin-LM-7B-V0.2-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
+```
+
+Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
+
+```shell
+pip3 install huggingface-hub
+```
+
+```python
+from huggingface_hub import InferenceClient
+
+endpoint_url = "https://your-endpoint-url-here"
+
+prompt = "Tell me about AI"
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+'''
+
+client = InferenceClient(endpoint_url)
+response = client.text_generation(prompt,
+                                  max_new_tokens=128,
+                                  do_sample=True,
+                                  temperature=0.7,
+                                  top_p=0.95,
+                                  top_k=40,
+                                  repetition_penalty=1.1)
+
+print(f"Model output: ", response)
+```
+<!-- README_AWQ.md-use-from-tgi end -->
+
+<!-- README_AWQ.md-use-from-python start -->
+## Inference from Python code using AutoAWQ
+
+### Install the AutoAWQ package
+
+Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.1 or later.
+
+```shell
+pip3 install autoawq
+```
+
+If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
+
+```shell
+pip3 uninstall -y autoawq
+git clone https://github.com/casper-hansen/AutoAWQ
+cd AutoAWQ
+pip3 install .
+```
+
+### AutoAWQ example code
+
+```python
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer
+
+model_name_or_path = "TheBloke/Xwin-LM-7B-V0.2-AWQ"
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
+# Load model
+model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
+                                          trust_remote_code=False, safetensors=True)
+
+prompt = "Tell me about AI"
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+'''
+
+print("*** Running model.generate:")
+
+token_input = tokenizer(
+    prompt_template,
+    return_tensors='pt'
+).input_ids.cuda()
+
+# Generate output
+generation_output = model.generate(
+    token_input,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    max_new_tokens=512
+)
+
+# Get the tokens from the output, decode them, print them
+token_output = generation_output[0]
+text_output = tokenizer.decode(token_output)
+print("LLM output: ", text_output)
+
+"""
+# Inference should be possible with transformers pipeline as well in future
+# But currently this is not yet supported by AutoAWQ (correct as of September 25th 2023)
+from transformers import pipeline
+
+print("*** Pipeline:")
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    top_k=40,
+    repetition_penalty=1.1
+)
+
+print(pipe(prompt_template)[0]['generated_text'])
+"""
+```
+<!-- README_AWQ.md-use-from-python end -->
+
+<!-- README_AWQ.md-compatibility start -->
+## Compatibility
+
+The files provided are tested to work with:
+
+- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
+- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
+
+<!-- README_AWQ.md-compatibility end -->
+
+<!-- footer start -->
+<!-- 200823 -->
+## Discord
+
+For further support, and discussions on these models and AI in general, join us at:
+
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
+
+## Thanks, and how to contribute
+
+Thanks to the [chirper.ai](https://chirper.ai) team!
+
+Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
+
+I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
+
+If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
+
+Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
+
+* Patreon: https://patreon.com/TheBlokeAI
+* Ko-Fi: https://ko-fi.com/TheBlokeAI
+
+**Special thanks to**: Aemon Algiz.
+
+**Patreon special mentions**: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
+
+
+Thank you to all my generous patrons and donaters!
+
+And thank you again to a16z for their generous grant.
+
+<!-- footer end -->
+
+# Original model card: Xwin-LM's Xwin LM 7B v0.2
+
+
+<h3 align="center">
+Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
+</h3>
+
+<p align="center">
+  <a href="https://github.com/Xwin-LM/Xwin-LM"><img src="https://img.shields.io/badge/GitHub-yellow.svg?style=social&logo=github"></a><a href="https://huggingface.co/Xwin-LM"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue"></a>
+</p>
+
+
+
+
+**Step up your LLM alignment with Xwin-LM!**
+
+Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models (RM), reject sampling, reinforcement learning from human feedback (RLHF), etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
+
+## News
+
+- 💥 [Oct 12, 2023] [Xwin-LM-7B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2) and [Xwin-LM-13B-V0.2](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2) have been released, with improved comparison data and RL training (i.e., PPO). Their winrates v.s. GPT-4 have increased significantly, reaching **59.83%** (7B model) and **70.36%** (13B model) respectively. The 70B model will be released soon.
+- 💥 [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
+- 🔍 [Sep, 2023] RLHF plays crucial role in the strong performance of Xwin-LM-V0.1 release!
+- 💥 [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
+- 💥 [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
+
+
+## Model Card
+| Model        | Checkpoint | Report | License  |
+|------------|------------|-------------|------------------|
+|Xwin-LM-7B-V0.2| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.2" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-13B-V0.2| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.2" target="_blank">HF Link</a> |  |  <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> |  | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> |  |  <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> |  |  <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
+## Benchmarks
+
+### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
+
+The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
+
+| **Model**                         | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)**  |**AlpacaEval (winrate %)** |
+|----------------------------------|------------|----------|-------------|
+|    | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
+| **Xwin-LM-70B-V0.1**                   | **95.57**      | **87.50**          | **60.61**            |
+| GPT-4                          | 95.28  | 84.66     |  50.00      |
+| **Xwin-LM-13B-V0.2**          | **93.22**  | **87.14**  |  **70.36**    |
+| WizardLM-70B-V1.0           | 92.91  | 80.19     |  46.70      |
+| Llama-2-70B-Chat         | 92.66  | 81.97     |  51.19      |
+| **Xwin-LM-13B-V0.1**          | **91.76**  | **81.79**  |  **55.30**    |
+| ChatGPT                    | 89.37  | 50.00     |  16.60      |
+| **Xwin-LM-7B-V0.2**      | **89.31** | **79.60**    |  **59.83**     |
+| WizardLM-13B-V1.2         | 89.17  | 75.75     |  41.91      |
+| **Xwin-LM-7B-V0.1**      | **87.35** | **76.40**    |  **47.57**     |
+| Llama-2-13B-Chat     | 81.09  | 64.22     |  30.92      |
+
+
+### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
+
+|   Prompts  |  GPT4 response   |  Xwin-LM response |
+|----------------|------------|--------|
+|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
+| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
+
+
+### Xwin-LM performance on NLP foundation tasks.
+
+The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks in [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). 
+
+| Model            | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average    |
+|------------------|-------------|-------------|-------------------|-------------------|------------|
+| Text-davinci-003 | 56.9 | **85.2**    | 59.3         | 82.2       | 70.9  |
+|Vicuna-13b 1.1   | 51.3        | 53.0        | 51.8              | 80.1              | 59.1       |
+|Guanaco 30B   | 57.6        | 63.7        | 50.7              | 85.1              | 64.3       |   
+| WizardLM-7B 1.0      | 42.7        | 51.6        | 44.7              | 77.7              | 54.2       |
+| WizardLM-13B 1.0     | 52.3        | 57.2        | 50.5              | 81.0              | 60.2       |
+| WizardLM-30B 1.0    | 58.8    | 62.5 | 52.4       | 83.3          | 64.2|
+| Llama-2-7B-Chat      | 48.3        | 52.9        | 45.6     | 78.6    | 56.4       |
+| Llama-2-13B-Chat      | 54.6        | 59.0        | 44.1     | 81.9    | 59.9       |
+| Llama-2-70B-Chat      | 63.9        | 64.6        | 52.8       | 85.9   | 66.8       |
+| **Xwin-LM-7B-V0.1**      | 49.7        | 56.2        | 48.1     | 79.5    | 58.4       |
+| **Xwin-LM-13B-V0.1**      | 56.6        | 62.4        | 45.5     | 83.0    | 61.9       |
+| **Xwin-LM-70B-V0.1**      | **69.6**        | 70.5        | **60.1**       | **87.1**   | **71.8**       |
+| **Xwin-LM-7B-V0.2**      | 50.0  | 56.4    |  49.5   |  78.9   |     58.7       |
+| **Xwin-LM-13B-V0.2**      | 56.6 |    61.5   |  43.8   | 82.9  |         61.2      |
+
+
+## Inference
+
+### Conversation Template
+To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
+```
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
+```
+
+### HuggingFace Example
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
+tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
+(
+    prompt := "A chat between a curious user and an artificial intelligence assistant. "
+            "The assistant gives helpful, detailed, and polite answers to the user's questions. "
+            "USER: Hello, can you help me? "
+            "ASSISTANT:"
+)
+inputs = tokenizer(prompt, return_tensors="pt")
+samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
+output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+print(output) 
+# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
+```
+
+
+### vLLM Example
+Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vLLM](https://github.com/vllm-project/vllm). Please refer to [vLLM](https://github.com/vllm-project/vllm) for detailed installation instructions.
+```python
+from vllm import LLM, SamplingParams
+(
+    prompt := "A chat between a curious user and an artificial intelligence assistant. "
+            "The assistant gives helpful, detailed, and polite answers to the user's questions. "
+            "USER: Hello, can you help me? "
+            "ASSISTANT:"
+)
+sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
+llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
+outputs = llm.generate([prompt,], sampling_params)
+
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(generated_text)
+```
+
+## TODO
+
+- [ ] Release the source code
+- [ ] Release more capabilities, such as math, reasoning, and etc.
+
+## Citation
+Please consider citing our work if you use the data or code in this repo.
+```
+@software{xwin-lm,
+  title = {Xwin-LM},
+  author = {Xwin-LM Team},
+  url = {https://github.com/Xwin-LM/Xwin-LM},
+  version = {pre-release},
+  year = {2023},
+  month = {9},
+}
+```
+
+## Acknowledgements
+
+Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vLLM](https://github.com/vllm-project/vllm).