初始化项目，由ModelHub XC社区提供模型
Model: TheBloke/Swallow-7B-Instruct-AWQ Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
126
LICENSE.txt
Normal file
126
LICENSE.txt
Normal file
@@ -0,0 +1,126 @@
|
||||
LLAMA 2 COMMUNITY LICENSE AGREEMENT
|
||||
Llama 2 Version Release Date: July 18, 2023
|
||||
|
||||
"Agreement" means the terms and conditions for use, reproduction, distribution and
|
||||
modification of the Llama Materials set forth herein.
|
||||
|
||||
"Documentation" means the specifications, manuals and documentation
|
||||
accompanying Llama 2 distributed by Meta at ai.meta.com/resources/models-and-
|
||||
libraries/llama-downloads/.
|
||||
|
||||
"Licensee" or "you" means you, or your employer or any other person or entity (if
|
||||
you are entering into this Agreement on such person or entity's behalf), of the age
|
||||
required under applicable laws, rules or regulations to provide legal consent and that
|
||||
has legal authority to bind your employer or such other person or entity if you are
|
||||
entering in this Agreement on their behalf.
|
||||
|
||||
"Llama 2" means the foundational large language models and software and
|
||||
algorithms, including machine-learning model code, trained model weights,
|
||||
inference-enabling code, training-enabling code, fine-tuning enabling code and other
|
||||
elements of the foregoing distributed by Meta at ai.meta.com/resources/models-and-
|
||||
libraries/llama-downloads/.
|
||||
|
||||
"Llama Materials" means, collectively, Meta's proprietary Llama 2 and
|
||||
Documentation (and any portion thereof) made available under this Agreement.
|
||||
|
||||
"Meta" or "we" means Meta Platforms Ireland Limited (if you are located in or, if you
|
||||
are an entity, your principal place of business is in the EEA or Switzerland) and Meta
|
||||
Platforms, Inc. (if you are located outside of the EEA or Switzerland).
|
||||
|
||||
By clicking "I Accept" below or by using or distributing any portion or element of the
|
||||
Llama Materials, you agree to be bound by this Agreement.
|
||||
|
||||
1. License Rights and Redistribution.
|
||||
|
||||
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-
|
||||
transferable and royalty-free limited license under Meta's intellectual property or
|
||||
other rights owned by Meta embodied in the Llama Materials to use, reproduce,
|
||||
distribute, copy, create derivative works of, and make modifications to the Llama
|
||||
Materials.
|
||||
|
||||
b. Redistribution and Use.
|
||||
|
||||
i. If you distribute or make the Llama Materials, or any derivative works
|
||||
thereof, available to a third party, you shall provide a copy of this Agreement to such
|
||||
third party.
|
||||
ii. If you receive Llama Materials, or any derivative works thereof, from
|
||||
a Licensee as part of an integrated end user product, then Section 2 of this
|
||||
Agreement will not apply to you.
|
||||
|
||||
iii. You must retain in all copies of the Llama Materials that you
|
||||
distribute the following attribution notice within a "Notice" text file distributed as a
|
||||
part of such copies: "Llama 2 is licensed under the LLAMA 2 Community License,
|
||||
Copyright (c) Meta Platforms, Inc. All Rights Reserved."
|
||||
|
||||
iv. Your use of the Llama Materials must comply with applicable laws
|
||||
and regulations (including trade compliance laws and regulations) and adhere to the
|
||||
Acceptable Use Policy for the Llama Materials (available at
|
||||
https://ai.meta.com/llama/use-policy), which is hereby incorporated by reference into
|
||||
this Agreement.
|
||||
|
||||
v. You will not use the Llama Materials or any output or results of the
|
||||
Llama Materials to improve any other large language model (excluding Llama 2 or
|
||||
derivative works thereof).
|
||||
|
||||
2. Additional Commercial Terms. If, on the Llama 2 version release date, the
|
||||
monthly active users of the products or services made available by or for Licensee,
|
||||
or Licensee's affiliates, is greater than 700 million monthly active users in the
|
||||
preceding calendar month, you must request a license from Meta, which Meta may
|
||||
grant to you in its sole discretion, and you are not authorized to exercise any of the
|
||||
rights under this Agreement unless or until Meta otherwise expressly grants you
|
||||
such rights.
|
||||
|
||||
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE
|
||||
LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE
|
||||
PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND,
|
||||
EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY
|
||||
WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR
|
||||
FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
|
||||
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING
|
||||
THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR
|
||||
USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
|
||||
|
||||
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE
|
||||
LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT,
|
||||
NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS
|
||||
AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL,
|
||||
CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
|
||||
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
|
||||
ANY OF THE FOREGOING.
|
||||
|
||||
5. Intellectual Property.
|
||||
|
||||
a. No trademark licenses are granted under this Agreement, and in
|
||||
connection with the Llama Materials, neither Meta nor Licensee may use any name
|
||||
or mark owned by or associated with the other or any of its affiliates, except as
|
||||
required for reasonable and customary use in describing and redistributing the
|
||||
Llama Materials.
|
||||
|
||||
b. Subject to Meta's ownership of Llama Materials and derivatives made by or
|
||||
for Meta, with respect to any derivative works and modifications of the Llama
|
||||
Materials that are made by you, as between you and Meta, you are and will be the
|
||||
owner of such derivative works and modifications.
|
||||
|
||||
c. If you institute litigation or other proceedings against Meta or any entity
|
||||
(including a cross-claim or counterclaim in a lawsuit) alleging that the Llama
|
||||
Materials or Llama 2 outputs or results, or any portion of any of the foregoing,
|
||||
constitutes infringement of intellectual property or other rights owned or licensable
|
||||
by you, then any licenses granted to you under this Agreement shall terminate as of
|
||||
the date such litigation or claim is filed or instituted. You will indemnify and hold
|
||||
harmless Meta from and against any claim by any third party arising out of or related
|
||||
to your use or distribution of the Llama Materials.
|
||||
|
||||
6. Term and Termination. The term of this Agreement will commence upon your
|
||||
acceptance of this Agreement or access to the Llama Materials and will continue in
|
||||
full force and effect until terminated in accordance with the terms and conditions
|
||||
herein. Meta may terminate this Agreement if you are in breach of any term or
|
||||
condition of this Agreement. Upon termination of this Agreement, you shall delete
|
||||
and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the
|
||||
termination of this Agreement.
|
||||
|
||||
7. Governing Law and Jurisdiction. This Agreement will be governed and
|
||||
construed under the laws of the State of California without regard to choice of law
|
||||
principles, and the UN Convention on Contracts for the International Sale of Goods
|
||||
does not apply to this Agreement. The courts of California shall have exclusive
|
||||
jurisdiction of any dispute arising out of this Agreement.
|
||||
|
||||
547
README.md
Normal file
547
README.md
Normal file
@@ -0,0 +1,547 @@
|
||||
---
|
||||
base_model: tokyotech-llm/Swallow-7b-instruct-hf
|
||||
inference: false
|
||||
language:
|
||||
- en
|
||||
- ja
|
||||
library_name: transformers
|
||||
license: llama2
|
||||
model_creator: tokyotech-llm
|
||||
model_name: Swallow 7B Instruct
|
||||
model_type: llama
|
||||
pipeline_tag: text-generation
|
||||
prompt_template: "\u4EE5\u4E0B\u306B\u3001\u3042\u308B\u30BF\u30B9\u30AF\u3092\u8AAC\
|
||||
\u660E\u3059\u308B\u6307\u793A\u304C\u3042\u308A\u307E\u3059\u3002\u30EA\u30AF\u30A8\
|
||||
\u30B9\u30C8\u3092\u9069\u5207\u306B\u5B8C\u4E86\u3059\u308B\u305F\u3081\u306E\u56DE\
|
||||
\u7B54\u3092\u8A18\u8FF0\u3057\u3066\u304F\u3060\u3055\u3044\u3002\\n\\n### \u6307\
|
||||
\u793A:\\n{prompt}\\n\\n### \u5FDC\u7B54:\n"
|
||||
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 -->
|
||||
|
||||
# Swallow 7B Instruct - AWQ
|
||||
- Model creator: [tokyotech-llm](https://huggingface.co/tokyotech-llm)
|
||||
- Original model: [Swallow 7B Instruct](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf)
|
||||
|
||||
<!-- description start -->
|
||||
## Description
|
||||
|
||||
This repo contains AWQ model files for [tokyotech-llm's Swallow 7B Instruct](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf).
|
||||
|
||||
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
|
||||
|
||||
|
||||
### 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.
|
||||
|
||||
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
|
||||
|
||||
It is supported by:
|
||||
|
||||
- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
|
||||
- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
|
||||
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
|
||||
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
|
||||
- [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/Swallow-7B-Instruct-AWQ)
|
||||
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Swallow-7B-Instruct-GPTQ)
|
||||
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Swallow-7B-Instruct-GGUF)
|
||||
* [tokyotech-llm's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf)
|
||||
<!-- repositories-available end -->
|
||||
|
||||
<!-- prompt-template start -->
|
||||
## Prompt template: Swallow-Instruct
|
||||
|
||||
```
|
||||
以下に、あるタスクを説明する指示があります。リクエストを適切に完了するための回答を記述してください。\n\n### 指示:\n{prompt}\n\n### 応答:
|
||||
|
||||
```
|
||||
|
||||
<!-- prompt-template end -->
|
||||
|
||||
|
||||
<!-- README_AWQ.md-provided-files start -->
|
||||
## Provided files, and AWQ parameters
|
||||
|
||||
I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
|
||||
|
||||
Models are released as sharded safetensors files.
|
||||
|
||||
| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
|
||||
| ------ | ---- | -- | ----------- | ------- | ---- |
|
||||
| [main](https://huggingface.co/TheBloke/Swallow-7B-Instruct-AWQ/tree/main) | 4 | 128 | [Alpaca Japanese](https://huggingface.co/datasets/fujiki/japanese_alpaca_data/viewer/) | 4096 | 4.07 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/Swallow-7B-Instruct-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: `Swallow-7B-Instruct-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 -m vllm.entrypoints.api_server --model TheBloke/Swallow-7B-Instruct-AWQ --quantization awq --dtype auto
|
||||
```
|
||||
|
||||
- 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'''以下に、あるタスクを説明する指示があります。リクエストを適切に完了するための回答を記述してください。\n\n### 指示:\n{prompt}\n\n### 応答:
|
||||
'''
|
||||
|
||||
prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
|
||||
|
||||
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
|
||||
|
||||
llm = LLM(model="TheBloke/Swallow-7B-Instruct-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/Swallow-7B-Instruct-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'''以下に、あるタスクを説明する指示があります。リクエストを適切に完了するための回答を記述してください。\n\n### 指示:\n{prompt}\n\n### 応答:
|
||||
'''
|
||||
|
||||
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 Transformers
|
||||
|
||||
### Install the necessary packages
|
||||
|
||||
- Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
|
||||
- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
|
||||
|
||||
```shell
|
||||
pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
|
||||
```
|
||||
|
||||
Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
|
||||
|
||||
If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
|
||||
|
||||
```shell
|
||||
pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
|
||||
```
|
||||
|
||||
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 .
|
||||
```
|
||||
|
||||
### Transformers example code (requires Transformers 4.35.0 and later)
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
|
||||
|
||||
model_name_or_path = "TheBloke/Swallow-7B-Instruct-AWQ"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name_or_path,
|
||||
low_cpu_mem_usage=True,
|
||||
device_map="cuda:0"
|
||||
)
|
||||
|
||||
# Using the text streamer to stream output one token at a time
|
||||
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
|
||||
|
||||
prompt = "Tell me about AI"
|
||||
prompt_template=f'''以下に、あるタスクを説明する指示があります。リクエストを適切に完了するための回答を記述してください。\n\n### 指示:\n{prompt}\n\n### 応答:
|
||||
'''
|
||||
|
||||
# Convert prompt to tokens
|
||||
tokens = tokenizer(
|
||||
prompt_template,
|
||||
return_tensors='pt'
|
||||
).input_ids.cuda()
|
||||
|
||||
generation_params = {
|
||||
"do_sample": True,
|
||||
"temperature": 0.7,
|
||||
"top_p": 0.95,
|
||||
"top_k": 40,
|
||||
"max_new_tokens": 512,
|
||||
"repetition_penalty": 1.1
|
||||
}
|
||||
|
||||
# Generate streamed output, visible one token at a time
|
||||
generation_output = model.generate(
|
||||
tokens,
|
||||
streamer=streamer,
|
||||
**generation_params
|
||||
)
|
||||
|
||||
# Generation without a streamer, which will include the prompt in the output
|
||||
generation_output = model.generate(
|
||||
tokens,
|
||||
**generation_params
|
||||
)
|
||||
|
||||
# Get the tokens from the output, decode them, print them
|
||||
token_output = generation_output[0]
|
||||
text_output = tokenizer.decode(token_output)
|
||||
print("model.generate output: ", text_output)
|
||||
|
||||
# Inference is also possible via Transformers' pipeline
|
||||
from transformers import pipeline
|
||||
|
||||
pipe = pipeline(
|
||||
"text-generation",
|
||||
model=model,
|
||||
tokenizer=tokenizer,
|
||||
**generation_params
|
||||
)
|
||||
|
||||
pipe_output = pipe(prompt_template)[0]['generated_text']
|
||||
print("pipeline output: ", pipe_output)
|
||||
|
||||
```
|
||||
<!-- 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.
|
||||
- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 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**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
|
||||
|
||||
|
||||
Thank you to all my generous patrons and donaters!
|
||||
|
||||
And thank you again to a16z for their generous grant.
|
||||
|
||||
<!-- footer end -->
|
||||
|
||||
# Original model card: tokyotech-llm's Swallow 7B Instruct
|
||||
|
||||
|
||||
# Swallow
|
||||
|
||||
Our Swallow model has undergone continuous pre-training from the Llama 2 family, primarily with the addition of Japanese language data. The tuned versions use supervised fine-tuning (SFT).
|
||||
Links to other models can be found in the index.
|
||||
|
||||
## Swallow Model Index
|
||||
|Model|Swallow-hf|Swallow-instruct-hf|
|
||||
|---|---|---|
|
||||
|7B| [Link](https://huggingface.co/tokyotech-llm/Swallow-7b-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-7b-instruct-hf)|
|
||||
|13B| [Link](https://huggingface.co/tokyotech-llm/Swallow-13b-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-13b-instruct-hf)|
|
||||
|70B| [Link](https://huggingface.co/tokyotech-llm/Swallow-70b-hf) | [Link](https://huggingface.co/tokyotech-llm/Swallow-70b-instruct-hf)|
|
||||
|
||||
|
||||
|
||||
|
||||
This repository provides large language models developed by [TokyoTech-LLM](https://tokyotech-llm.github.io/).
|
||||
Read our [blog post](https://zenn.dev/tokyotech_lm/articles/d6cb3a8fdfc907) or our paper (preprint coming soon) for more details!
|
||||
|
||||
|
||||
## Model Details
|
||||
|
||||
* **Model type**: Please refer to LLaMA-2 technical report for details on the model architecture.
|
||||
* **Language(s)**: Japanese English
|
||||
* **Library**: [Megatron-LM](https://github.com/rioyokotalab/Megatron-Llama2)
|
||||
* **Tokenizer**: This model employs a tokenizer that features a broadened vocabulary based on Japanese data. This allows for a more efficient representation of text using fewer tokens, leading to a notably faster inference process.
|
||||
* **Contact**: swallow[at]nlp.c.titech.ac.jp
|
||||
|
||||
## Base Model Performance
|
||||
|
||||
### Japanese version
|
||||
|
||||
|Model|Size|JCommonsenseQA|JEMHopQA|NIILC|JSQuAD|XL-Sum|MGSM|WMT20-en-ja|WMT20-ja-en|
|
||||
|---|---|---|---|---|---|---|---|---|---|
|
||||
| | |4-shot|4-shot|4-shot|4-shot|1-shot|4-shot|4-shot|4-shot|
|
||||
|Llama 2|7B|0.3852|0.4240|0.3410|0.7917|0.1905|0.0760|0.1783|0.1738|
|
||||
|Swallow|7B|0.4808|0.5078|0.5968|0.8573|0.1830|0.1240|0.2510|0.1511|
|
||||
|Llama 2|13B|0.6997|0.4415|0.4170|0.8533|0.2139|0.1320|0.2146|0.1982|
|
||||
|Swallow|13B|0.7837|0.5063|0.6398|0.9005|0.2168|0.2040|0.2720|0.1771|
|
||||
|Llama 2|70B|0.8686|0.4656|0.5256|0.9080|**0.2361**|0.3560|0.2643|**0.2398**|
|
||||
|Swallow|70B|**0.9348**|**0.6290**|**0.6960**|**0.9176**|0.2266|**0.4840**|**0.3043**|0.2298|
|
||||
|
||||
## Usage
|
||||
|
||||
First install additional dependencies in [requirements.txt](./requirements.txt):
|
||||
|
||||
```sh
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
### Use the instruct model
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "tokyotech-llm/Swallow-7b-instruct-hf"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, device_map="auto")
|
||||
|
||||
|
||||
PROMPT_DICT = {
|
||||
"prompt_input": (
|
||||
"以下に、あるタスクを説明する指示があり、それに付随する入力が更なる文脈を提供しています。"
|
||||
"リクエストを適切に完了するための回答を記述してください。\n\n"
|
||||
"### 指示:\n{instruction}\n\n### 入力:\n{input}\n\n### 応答:"
|
||||
|
||||
),
|
||||
"prompt_no_input": (
|
||||
"以下に、あるタスクを説明する指示があります。"
|
||||
"リクエストを適切に完了するための回答を記述してください。\n\n"
|
||||
"### 指示:\n{instruction}\n\n### 応答:"
|
||||
),
|
||||
}
|
||||
|
||||
def create_prompt(instruction, input=None):
|
||||
"""
|
||||
Generates a prompt based on the given instruction and an optional input.
|
||||
If input is provided, it uses the 'prompt_input' template from PROMPT_DICT.
|
||||
If no input is provided, it uses the 'prompt_no_input' template.
|
||||
|
||||
Args:
|
||||
instruction (str): The instruction describing the task.
|
||||
input (str, optional): Additional input providing context for the task. Default is None.
|
||||
|
||||
Returns:
|
||||
str: The generated prompt.
|
||||
"""
|
||||
if input:
|
||||
# Use the 'prompt_input' template when additional input is provided
|
||||
return PROMPT_DICT["prompt_input"].format(instruction=instruction, input=input)
|
||||
else:
|
||||
# Use the 'prompt_no_input' template when no additional input is provided
|
||||
return PROMPT_DICT["prompt_no_input"].format(instruction=instruction)
|
||||
|
||||
# Example usage
|
||||
instruction_example = "以下のトピックに関する詳細な情報を提供してください。"
|
||||
input_example = "東京工業大学の主なキャンパスについて教えてください"
|
||||
prompt = create_prompt(instruction_example, input_example)
|
||||
|
||||
input_ids = tokenizer.encode(
|
||||
prompt,
|
||||
add_special_tokens=False,
|
||||
return_tensors="pt"
|
||||
)
|
||||
|
||||
tokens = model.generate(
|
||||
input_ids.to(device=model.device),
|
||||
max_new_tokens=128,
|
||||
temperature=0.99,
|
||||
top_p=0.95,
|
||||
do_sample=True,
|
||||
)
|
||||
|
||||
out = tokenizer.decode(tokens[0], skip_special_tokens=True)
|
||||
print(out)
|
||||
|
||||
```
|
||||
|
||||
### Use the base model
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "tokyotech-llm/Swallow-7b-hf"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
prompt = "東京工業大学の主なキャンパスは、"
|
||||
input_ids = tokenizer.encode(
|
||||
prompt,
|
||||
add_special_tokens=False,
|
||||
return_tensors="pt"
|
||||
)
|
||||
tokens = model.generate(
|
||||
input_ids.to(device=model.device),
|
||||
max_new_tokens=128,
|
||||
temperature=0.99,
|
||||
top_p=0.95,
|
||||
do_sample=True,
|
||||
)
|
||||
|
||||
out = tokenizer.decode(tokens[0], skip_special_tokens=True)
|
||||
print(out)
|
||||
```
|
||||
|
||||
## Training Datasets
|
||||
|
||||
### Continual Pre-Training
|
||||
The following datasets were used for continual pre-training.
|
||||
|
||||
- [Japanese Wikipedia](https://dumps.wikimedia.org/other/cirrussearch)
|
||||
- [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)
|
||||
- Swallow Corpus
|
||||
- [The Pile](https://huggingface.co/datasets/EleutherAI/pile)
|
||||
|
||||
|
||||
### Instruction Tuning
|
||||
|
||||
The following datasets were used for the instruction tuning.
|
||||
|
||||
- [Anthropic HH-RLHF](https://huggingface.co/datasets/kunishou/hh-rlhf-49k-ja)
|
||||
- [Databricks Dolly 15-k](https://huggingface.co/datasets/kunishou/databricks-dolly-15k-ja)
|
||||
- [OpenAssistant Conversations Dataset](https://huggingface.co/datasets/kunishou/oasst1-89k-ja)
|
||||
|
||||
## Risks and Limitations
|
||||
|
||||
The models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.
|
||||
|
||||
## Acknowledgements
|
||||
|
||||
We thank Meta Research for releasing Llama 2 under an open license for others to build on.
|
||||
|
||||
Our project is supported by the [ABCI Large-scale Language Model Building Support Program](https://abci.ai/en/link/llm_support_program.html) of the National Institute of Advanced Industrial Science and Technology.
|
||||
|
||||
## License
|
||||
|
||||
Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
|
||||
|
||||
## Authors
|
||||
|
||||
Here are the team members:
|
||||
- From [Okazaki Laboratory](https://www.nlp.c.titech.ac.jp/index.en.html), the following members:
|
||||
- [Naoaki Okazaki](https://www.chokkan.org/index.ja.html)
|
||||
- [Sakae Mizuki](https://s-mizuki-nlp.github.io/)
|
||||
- [Hiroki Iida](https://meshidenn.github.io/)
|
||||
- [Mengsay Loem](https://loem-ms.github.io/)
|
||||
- [Shota Hirai](https://huggingface.co/Kotemo428)
|
||||
- [Kakeru Hattori](https://aya-se.vercel.app/)
|
||||
- [Masanari Ohi](https://twitter.com/stjohn2007)
|
||||
- From [YOKOTA Laboratory](https://www.rio.gsic.titech.ac.jp/en/index.html), the following members:
|
||||
- [Rio Yokota](https://twitter.com/rioyokota)
|
||||
- [Kazuki Fujii](https://twitter.com/okoge_kaz)
|
||||
- [Taishi Nakamura](https://twitter.com/Setuna7777_2)
|
||||
36
config.json
Normal file
36
config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"_name_or_path": "/workspace/process/tokyotech-llm_swallow-7b-instruct-hf/source",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"max_sequence_length": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"quant_method": "awq",
|
||||
"version": "gemm",
|
||||
"zero_point": true
|
||||
},
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 43176
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
11
generation_config.json
Normal file
11
generation_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"temperature": 0.6,
|
||||
"max_length": 4096,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.33.2"
|
||||
}
|
||||
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9d0e829ff7e61451146cca7c9464146a7d945b5ab5666e0900aaab05fde0919
|
||||
size 4072499096
|
||||
6
quant_config.json
Normal file
6
quant_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"zero_point": true,
|
||||
"q_group_size": 128,
|
||||
"w_bit": 4,
|
||||
"version": "GEMM"
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
114818
tokenizer.json
Normal file
114818
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c877c5ca885bad5c19d1b1706a2703f8b30de90f03c1f834f8bdb9faf79821e8
|
||||
size 914000
|
||||
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user