Upload README.md

README.md

@@ -5,16 +5,9 @@ license: llama2
 model_creator: Xwin-LM
 model_name: Xwin-LM 13B V0.1
 model_type: llama
-prompt_template: 'Below is an instruction that describes a task. Write a response
-  that appropriately completes the request.
-
-
-  ### Instruction:
-
-  {prompt}
-
-
-  ### Response:
+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
@@ -59,15 +52,10 @@ Multiple GPTQ parameter permutations are provided; see Provided Files below for
 <!-- repositories-available end -->
 
 <!-- prompt-template start -->
-## Prompt template: Alpaca
+## Prompt template: Vicuna
 
 ```
-Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
-{prompt}
-
-### Response:
+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:
 
 ```
 
@@ -75,7 +63,7 @@ Below is an instruction that describes a task. Write a response that appropriate
 
 
 <!-- README_GPTQ.md-provided-files start -->
-## Provided files and GPTQ parameters
+## Provided files, and GPTQ parameters
 
 Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
 
@@ -90,8 +78,8 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
 - GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
 - Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
 - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
-- GPTQ dataset: The dataset used for quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
-- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used.  Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
+- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
+- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
 - ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
 
 </details>
@@ -107,14 +95,71 @@ All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches
 <!-- README_GPTQ.md-provided-files end -->
 
 <!-- README_GPTQ.md-download-from-branches start -->
-## How to download from branches
+## How to download, including from branches
+
+### In text-generation-webui
+
+To download from the `main` branch, enter `TheBloke/Xwin-LM-13B-V0.1-GPTQ` in the "Download model" box.
+
+To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Xwin-LM-13B-V0.1-GPTQ:main`
 
-- In text-generation-webui, you can add `:branch` to the end of the download name, eg `TheBloke/Xwin-LM-13B-V0.1-GPTQ:main`
-- With Git, you can clone a branch with:
+### From the command line
+
+I recommend using the `huggingface-hub` Python library:
+
+```shell
+pip3 install huggingface-hub
+```
+
+To download the `main` branch to a folder called `Xwin-LM-13B-V0.1-GPTQ`:
+
+```shell
+mkdir  Xwin-LM-13B-V0.1-GPTQ
+huggingface-cli download TheBloke/Xwin-LM-13B-V0.1-GPTQ --local-dir Xwin-LM-13B-V0.1-GPTQ --local-dir-use-symlinks False
 ```
+
+To download from a different branch, add the `--revision` parameter:
+
+```shell
+mkdir  Xwin-LM-13B-V0.1-GPTQ
+huggingface-cli download TheBloke/Xwin-LM-13B-V0.1-GPTQ --revision main --local-dir Xwin-LM-13B-V0.1-GPTQ --local-dir-use-symlinks False
+```
+
+<details>
+  <summary>More advanced huggingface-cli download usage</summary>
+
+If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
+
+The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
+
+For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
+
+To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
+
+```shell
+pip3 install hf_transfer
+```
+
+And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
+
+```shell
+mkdir  Xwin-LM-13B-V0.1-GPTQ
+HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Xwin-LM-13B-V0.1-GPTQ --local-dir Xwin-LM-13B-V0.1-GPTQ --local-dir-use-symlinks False
+```
+
+Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
+</details>
+
+### With `git` (**not** recommended)
+
+To clone a specific branch with `git`, use a command like this:
+
+```shell
 git clone --single-branch --branch main https://huggingface.co/TheBloke/Xwin-LM-13B-V0.1-GPTQ
 ```
-- In Python Transformers code, the branch is the `revision` parameter; see below.
+
+Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
+
 <!-- README_GPTQ.md-download-from-branches end -->
 <!-- README_GPTQ.md-text-generation-webui start -->
 ## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
@@ -142,10 +187,10 @@ It is strongly recommended to use the text-generation-webui one-click-installers
 
 ### Install the necessary packages
 
-Requires: Transformers 4.32.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
+Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
 
 ```shell
-pip3 install transformers>=4.32.0 optimum>=1.12.0
+pip3 install transformers optimum
 pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/  # Use cu117 if on CUDA 11.7
 ```
 
@@ -155,17 +200,10 @@ If you have problems installing AutoGPTQ using the pre-built wheels, install it
 pip3 uninstall -y auto-gptq
 git clone https://github.com/PanQiWei/AutoGPTQ
 cd AutoGPTQ
+git checkout v0.4.2
 pip3 install .
 ```
 
-### For CodeLlama models only: you must use Transformers 4.33.0 or later.
-
-If 4.33.0 is not yet released when you read this, you will need to install Transformers from source:
-```shell
-pip3 uninstall -y transformers
-pip3 install git+https://github.com/huggingface/transformers.git
-```
-
 ### You can then use the following code
 
 ```python
@@ -182,13 +220,7 @@ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
 
 prompt = "Tell me about AI"
-prompt_template=f'''Below is an instruction that describes a task. Write a response that appropriately completes the request.
-
-### Instruction:
-{prompt}
-
-### Response:
-
+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("\n\n*** Generate:")
@@ -268,6 +300,9 @@ 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>
@@ -277,13 +312,14 @@ Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
 
 **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, reject sampling, reinforcement learning, 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.
+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
 
-- :boom: [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**.
-- :boom: [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.
-- :boom: [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.
+- 💥 [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
@@ -311,4 +347,101 @@ The table below displays the performance of Xwin-LM on [AlpacaEval](https://tats
 | **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  |  GTP4 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**       |
+
+
+## Inference
+
+### Conversation templates
+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).