初始化项目，由ModelHub XC社区提供模型
Model: TheBloke/em_german_7b_v01-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
Normal file
126
LICENSE
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.
|
||||
|
||||
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.
|
||||
|
||||
1
Notice
Normal file
1
Notice
Normal file
@@ -0,0 +1 @@
|
||||
Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.
|
||||
624
README.md
Normal file
624
README.md
Normal file
@@ -0,0 +1,624 @@
|
||||
---
|
||||
base_model: jphme/em_german_7b_v01
|
||||
inference: false
|
||||
language:
|
||||
- de
|
||||
library_name: transformers
|
||||
license: llama2
|
||||
model_creator: Jan Philipp Harries
|
||||
model_name: EM German 7B v01
|
||||
model_type: llama
|
||||
pipeline_tag: text-generation
|
||||
prompt_template: 'Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT:
|
||||
|
||||
'
|
||||
quantized_by: TheBloke
|
||||
tags:
|
||||
- facebook
|
||||
- meta
|
||||
- pytorch
|
||||
- llama
|
||||
- llama-2
|
||||
- german
|
||||
- deutsch
|
||||
---
|
||||
|
||||
<!-- 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 -->
|
||||
|
||||
# EM German 7B v01 - AWQ
|
||||
- Model creator: [Jan Philipp Harries](https://huggingface.co/jphme)
|
||||
- Original model: [EM German 7B v01](https://huggingface.co/jphme/em_german_7b_v01)
|
||||
|
||||
<!-- description start -->
|
||||
## Description
|
||||
|
||||
This repo contains AWQ model files for [Jan Philipp Harries's EM German 7B v01](https://huggingface.co/jphme/em_german_7b_v01).
|
||||
|
||||
|
||||
### 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.
|
||||
|
||||
It is also now supported by continuous batching server [vLLM](https://github.com/vllm-project/vllm), allowing use of Llama AWQ models for high-throughput concurrent inference in multi-user server scenarios.
|
||||
|
||||
As of September 25th 2023, preliminary Llama-only AWQ support has also been added to [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference).
|
||||
|
||||
Note that, at the time of writing, overall throughput is still lower than running vLLM or TGI with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.
|
||||
<!-- description end -->
|
||||
<!-- repositories-available start -->
|
||||
## Repositories available
|
||||
|
||||
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/em_german_7b_v01-AWQ)
|
||||
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/em_german_7b_v01-GPTQ)
|
||||
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/em_german_7b_v01-GGUF)
|
||||
* [Jan Philipp Harries's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jphme/em_german_7b_v01)
|
||||
<!-- repositories-available end -->
|
||||
|
||||
<!-- prompt-template start -->
|
||||
## Prompt template: EmGerman
|
||||
|
||||
```
|
||||
Du bist ein hilfreicher Assistent. 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/em_german_7b_v01-AWQ/tree/main) | 4 | 128 | [German Quad](https://huggingface.co/datasets/deepset/germanquad) | 4096 | 3.89 GB
|
||||
|
||||
<!-- README_AWQ.md-provided-files end -->
|
||||
|
||||
<!-- README_AWQ.md-use-from-vllm start -->
|
||||
## Serving this model from vLLM
|
||||
|
||||
Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
|
||||
|
||||
Note: at the time of writing, vLLM has not yet done a new release with AWQ support.
|
||||
|
||||
If you try the vLLM examples below and get an error about `quantization` being unrecognised, or other AWQ-related issues, please install vLLM from Github source.
|
||||
|
||||
- When using vLLM as a server, pass the `--quantization awq` parameter, for example:
|
||||
|
||||
```shell
|
||||
python3 python -m vllm.entrypoints.api_server --model TheBloke/em_german_7b_v01-AWQ --quantization awq --dtype half
|
||||
```
|
||||
|
||||
When using vLLM from Python code, pass the `quantization=awq` parameter, for example:
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
|
||||
prompts = [
|
||||
"Hello, my name is",
|
||||
"The president of the United States is",
|
||||
"The capital of France is",
|
||||
"The future of AI is",
|
||||
]
|
||||
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
|
||||
|
||||
llm = LLM(model="TheBloke/em_german_7b_v01-AWQ", quantization="awq", dtype="half")
|
||||
|
||||
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 -->
|
||||
## Serving this model from 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/em_german_7b_v01-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 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'''Du bist ein hilfreicher Assistent. 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 -->
|
||||
## How to use this AWQ model from Python code
|
||||
|
||||
### Install the necessary packages
|
||||
|
||||
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 .
|
||||
```
|
||||
|
||||
### You can then try the following example code
|
||||
|
||||
```python
|
||||
from awq import AutoAWQForCausalLM
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
model_name_or_path = "TheBloke/em_german_7b_v01-AWQ"
|
||||
|
||||
# Load model
|
||||
model = AutoAWQForCausalLM.from_quantized(model_name_or_path, fuse_layers=True,
|
||||
trust_remote_code=False, safetensors=True)
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=False)
|
||||
|
||||
prompt = "Tell me about AI"
|
||||
prompt_template=f'''Du bist ein hilfreicher Assistent. USER: {prompt} ASSISTANT:
|
||||
|
||||
'''
|
||||
|
||||
print("\n\n*** Generate:")
|
||||
|
||||
tokens = tokenizer(
|
||||
prompt_template,
|
||||
return_tensors='pt'
|
||||
).input_ids.cuda()
|
||||
|
||||
# Generate output
|
||||
generation_output = model.generate(
|
||||
tokens,
|
||||
do_sample=True,
|
||||
temperature=0.7,
|
||||
top_p=0.95,
|
||||
top_k=40,
|
||||
max_new_tokens=512
|
||||
)
|
||||
|
||||
print("Output: ", tokenizer.decode(generation_output[0]))
|
||||
|
||||
"""
|
||||
# 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:
|
||||
|
||||
- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
|
||||
- [vLLM](https://github.com/vllm-project/vllm)
|
||||
- [Huggingface Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
|
||||
|
||||
TGI merged AWQ support on September 25th, 2023: [TGI PR #1054](https://github.com/huggingface/text-generation-inference/pull/1054). Use the `:latest` Docker container until the next TGI release is made.
|
||||
|
||||
<!-- 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: Jan Philipp Harries's EM German 7B v01
|
||||
|
||||
|
||||
|
||||
# EM German 7b
|
||||
|
||||
([Zur deutschen Version](#deutsch-em-german))
|
||||
|
||||
**EM German (v01)** is an experimental llama2-based model family, finetuned on a large dataset of various instructions in German language. The models are optimized for German text, providing proficiency in understanding, generating, and interacting with German language content.
|
||||
|
||||
**This 7b model has addtionally been pre-trained on >3bn high-quality tokens of German text**.
|
||||
|
||||
# Links & Demos
|
||||
|
||||
We will publish further instructions, updates and code-snippets in the project's [Github-Repo](https://github.com/jphme/EM_German).
|
||||
|
||||
## Model Links
|
||||
|
||||
| Base Model | HF | GPTQ | GGUF | AWQ |
|
||||
|-------|-------|-------|-------|-------|
|
||||
| [Llama2](https://huggingface.co/meta-llama/Llama-2-7b-hf) 7b | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gguf) | soon |
|
||||
| [Llama2](https://huggingface.co/meta-llama/Llama-2-13b-hf) 13b | [Link](https://huggingface.co/jphme/em_german_13b_v01) | [Link](https://huggingface.co/jphme/em_german_13b_v01_gptq) | soon | soon |
|
||||
| [Llama2](https://huggingface.co/meta-llama/Llama-2-70b-hf) 70b | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gguf) | soon |
|
||||
| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | soon | soon | tbc |
|
||||
| [LeoLm 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc |
|
||||
| [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc |
|
||||
|
||||
## Demos:
|
||||
|
||||
You can use some of the models with **free** google Colab instances (e.g. the 7bn model in 8bit or the 13b model with GPTQ):
|
||||
|
||||
* [Example Colab Notebook for 13b with GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing)
|
||||
* [Example Colab Notebook for 7b with 8bit-Loading](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing)
|
||||
* Further Examples for LLM apps will follow soon...
|
||||
|
||||
|
||||
# Prompt Format
|
||||
|
||||
This model follows the Vicuna format without linebreaks (but should work with linebreaks as well). The format is as follows:
|
||||
|
||||
```
|
||||
Du bist ein hilfreicher Assistent. USER: <instruction> ASSISTANT:
|
||||
```
|
||||
|
||||
You can swap the standard system prompt for a better suited one (see below for RAG-tasks).
|
||||
|
||||
# Results
|
||||
|
||||
Attached a few example outputs. I also developed a few small German benchmarks (based on the Eleuther LM Evaluation Harness), which I will publish soon.
|
||||
|
||||
## Example Output
|
||||
|
||||
Prompt:
|
||||
```
|
||||
Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT:
|
||||
```
|
||||
|
||||
Response EM 7b v01
|
||||
```
|
||||
Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert.
|
||||
|
||||
Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter
|
||||
|
||||
Das Buch enthält also insgesamt 150.000 Wörter.
|
||||
```
|
||||
|
||||
Prompt:
|
||||
```
|
||||
Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT:
|
||||
```
|
||||
|
||||
Response EM 7b v01
|
||||
```
|
||||
Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind.
|
||||
|
||||
1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern.
|
||||
|
||||
2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen.
|
||||
|
||||
3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist.
|
||||
|
||||
4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben.
|
||||
|
||||
|
||||
```
|
||||
|
||||
## Factual Retrieval / RAG
|
||||
|
||||
EM Models offer a special format for Factual Retrieval/RAG that is optimized for minimizing hallucinations. We use the same format as Airoboros for this:
|
||||
|
||||
### Example
|
||||
|
||||
Prompt
|
||||
```
|
||||
Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT
|
||||
BEGINCONTEXT
|
||||
Url: https://www.jph.me
|
||||
ENDCONTEXT
|
||||
Das Wetter in Düsseldorf wird heute schön und sonnig!
|
||||
ENDINPUT
|
||||
BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT:
|
||||
```
|
||||
|
||||
Model response:
|
||||
|
||||
```
|
||||
Mit den gegebenen Informationen ist diese Frage nicht zu beantworten.
|
||||
```
|
||||
Note that the model would normally always answer with the correct response to a trivial question like this but is trained to deny an answer, if there is no source between the BEGININPUT and ENDINPUT that provides a grounding.
|
||||
|
||||
If we keep the same Context/Input but ask instead:
|
||||
```
|
||||
BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT:
|
||||
```
|
||||
|
||||
We get the correct answer with the source:
|
||||
|
||||
```
|
||||
Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me)
|
||||
```
|
||||
|
||||
|
||||
# Evaluation
|
||||
I will publish some custom German benchmarks and the results for them soon.
|
||||
|
||||
# Dataset
|
||||
|
||||
The dataset is a mixture of multi-turn chats, retrieval instructions and synthetically generated instructions spawning many topics and applications.
|
||||
|
||||
|
||||
## Use with tranformers
|
||||
|
||||
Unchanged from the base model:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import LlamaForCausalLM, LlamaTokenizer
|
||||
|
||||
# Hugging Face model_path
|
||||
model_path = 'jphme/em_german_7b_v01'
|
||||
tokenizer = LlamaTokenizer.from_pretrained(model_path)
|
||||
model = LlamaForCausalLM.from_pretrained(
|
||||
model_path, torch_dtype=torch.float16, device_map='auto',
|
||||
)
|
||||
|
||||
def ask_model(instruction, system='Du bist ein hilfreicher Assistent.'):
|
||||
prompt=f"{system} USER: {instruction} ASSISTANT:"
|
||||
input_tokens=tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
output_tokens=model.generate(**input_tokens, max_new_tokens=200)[0]
|
||||
answer=tokenizer.decode(output_tokens, skip_special_tokens=True)
|
||||
return answer
|
||||
|
||||
print(ask_model("Nenne mir 10 gute Gründe dafür, heute Sport zu machen!"))
|
||||
```
|
||||
|
||||
# Limitations & Biases
|
||||
|
||||
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
|
||||
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
|
||||
|
||||
# Acknowledgements:
|
||||
|
||||
Many thanks to [winglian/caseus](https://huggingface.co/winglian) for his great work on Axolotl which I used to train the EM mdoels. I am also grateful to [Jon Durbin](https://huggingface.co/jondurbin) and his [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-70b-2.2.1) models and code from which I borrowed many ideas and code snippets.
|
||||
|
||||
The 70b model was trained with support of the [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/).
|
||||
|
||||
# Contact
|
||||
|
||||
I you are interested in customized LLMs for business applications, please get in contact with me via [my website](https://www.jph.me). I am also always happy about suggestions and feedback.
|
||||
|
||||
*PS: I am also still searching for a Co-Founder*.
|
||||
|
||||
# Disclaimer:
|
||||
|
||||
The license on this model does not constitute legal advice. I am not responsible for the actions of third parties who use this model.
|
||||
This model should only be used for research purposes. The original Llama2 license applies and is distributed with the model files.
|
||||
|
||||
-------------
|
||||
-------------
|
||||
-------------
|
||||
|
||||
# (Deutsch) EM German
|
||||
|
||||
**EM German (v01)** ist eine experimentelle, Llama2-basierte KI-Modellreihe, die in deutscher Sprache fine-getuned wurde.
|
||||
|
||||
Die Modelle sind für deutschen Text optimiert und können Inhalte in deutscher Sprache verstehen und generieren.
|
||||
|
||||
**Dieses 7b-Modell wurde zusätzlich mit >3 Milliarden Token deutscher Texte vortrainiert**.
|
||||
|
||||
# Links & Demos
|
||||
|
||||
Im [Github-Repo](https://github.com/jphme/EM_German) Repo werde ich weitere Beispiele und Code-Snippets veröffentlichen.
|
||||
|
||||
## Model Links
|
||||
|
||||
| Base Model | HF | GPTQ | GGUF | AWQ |
|
||||
|-------|-------|-------|-------|-------|
|
||||
| [Llama2](https://huggingface.co/meta-llama/Llama-2-7b-hf) 7b | [Link](https://huggingface.co/jphme/em_german_7b_v01) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_7b_v01_gguf) | soon |
|
||||
| [Llama2](https://huggingface.co/meta-llama/Llama-2-13b-hf) 13b | [Link](https://huggingface.co/jphme/em_german_13b_v01) | [Link](https://huggingface.co/jphme/em_german_13b_v01_gptq) | soon | soon |
|
||||
| [Llama2](https://huggingface.co/meta-llama/Llama-2-70b-hf) 70b | [Link](https://huggingface.co/jphme/em_german_70b_v01) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gptq) | [Link](https://huggingface.co/jphme/em_german_70b_v01_gguf) | soon |
|
||||
| [Mistral 7b](https://huggingface.co/mistralai/Mistral-7B-v0.1) | [Link](https://huggingface.co/jphme/em_german_mistral_v01) | soon | soon | tbc |
|
||||
| [LeoLm 7b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc |
|
||||
| [LeoLM 13b](https://huggingface.co/LeoLM/leo-hessianai-7b) | soon | soon | soon | tbc |
|
||||
|
||||
## Colab:
|
||||
|
||||
Einige der Modelle können mit kostenlosen Google Colab-Instanzen verwendet werden (z.B. das 7b-Modell in 8-Bit oder das 13b-Modell mit GPTQ):
|
||||
|
||||
* [Beispiel-Notebook 13b mit GPTQ](https://colab.research.google.com/drive/1IJfJdVwGkfe5MYOqHptystR3FBeEUdGn?usp=sharing)
|
||||
* [Beispiel-Notebook 7b mit 8-Bit](https://colab.research.google.com/drive/1bsv6vkLM4AlCpSyXA6ol9P32zxZmf7Zu?usp=sharing)
|
||||
* Weitere Beispiele für LLM-Apps folgen in Kürze...
|
||||
|
||||
# Eingabeformat
|
||||
|
||||
Dieses Modell folgt dem Vicuna-Format ohne Zeilenumbrüche (sollte aber auch mit Zeilenumbrüchen funktionieren). Das Format lautet wie folgt:
|
||||
|
||||
```
|
||||
Du bist ein hilfreicher Assistent. USER: <Anweisung> ASSISTANT:
|
||||
```
|
||||
|
||||
Sie können das Standard-Systemprompt aber auch ändern (siehe unten für ein Beispiel bei Aufgaben mit externen Datenbanken).
|
||||
|
||||
# Ergebnisse
|
||||
|
||||
Anbei einige Beispiele für Modell-Outputs. Wir werden demnächst einige kleine deutsche Benchmarks veröffentlichen (basierend auf dem Eleuther LM Evaluation Harness), die wir bei diesen Modellen bereits getstet haben.
|
||||
|
||||
## Beispiel-Ausgaben
|
||||
|
||||
Prompt:
|
||||
```
|
||||
Du bist ein hilfreicher Assistent USER: Ein Buch hat 500 Seiten. Jede Seite enthält 300 Wörter. Wie viele Wörter sind im gesamten Buch enthalten? ASSISTANT:
|
||||
```
|
||||
|
||||
Antwort EM 7b v01
|
||||
```
|
||||
Die Gesamtzahl der Wörter in dem Buch kann berechnet werden, indem man die Anzahl der Wörter pro Seite mit der Gesamtzahl der Seiten multipliziert.
|
||||
|
||||
Gesamtzahl der Wörter = Anzahl der Wörter pro Seite * Gesamtzahl der Seiten = 300 Wörter pro Seite * 500 Seiten = 150.000 Wörter
|
||||
|
||||
Das Buch enthält also insgesamt 150.000 Wörter.
|
||||
```
|
||||
|
||||
Prompt:
|
||||
```
|
||||
Du bist ein hilfreicher Assistent USER: Erläutere die Grundprinzipien der evolutionären Biologie und Genetik, indem du den Prozess der natürlichen Selektion, die Rolle von Mutationen und genetischer Drift sowie das Konzept der adaptiven Radiation erklärst. ASSISTANT:
|
||||
```
|
||||
|
||||
Antwort EM 7b v01:
|
||||
```
|
||||
Die Evolutionäre Biologie und Genetik sind zwei intim verwandte Disziplinen, die sich mit dem Studium des Verhaltens und der Entwicklung von Organismen in der Natur befassen. Sie untersuchen, wie Arten sich im Laufe der Zeit entwickeln und wie diese Veränderungen genetisch bedingt sind.
|
||||
|
||||
1. Natürliche Selektion: Die natürliche Selektion ist ein grundlegendes Prinzip in der Evolutionäre Biologie. Es besagt, dass Individuen innerhalb einer Spezies unterschiedliche Fähigkeiten oder Merkmale aufweisen können. Diese Merkmale beeinflussen ihre Überlebens- und Fortpflanzungsrate. Diejenigen mit Vorteilen haben eine höhere Wahrscheinlichkeit, ihre Gene an zukünftige Generationen weiterzugeben und so die Art im Laufe der Zeit zu verändern.
|
||||
|
||||
2. Rolle von Mutationen: Mutationen sind Veränderungen im Genom eines Organismus, die entweder durch zufällige Fehler während der Replikation oder durch Exposition gegenüber Strahlung verursacht werden. Diese Veränderungen können dazu führen, dass ein Individuum neue Eigenschaften aufweist, die es im Kampf ums Überleben vorteilhaft machen könnten. Diese Mutationen werden dann von der natürlichen Selektion beeinflusst und können so zur Entwicklung neuer Arten beitragen.
|
||||
|
||||
3. Genetische Drift: Genetische Drift ist ein zufälliger Prozess, der durch die Verteilung von Allelen in einer Population stattfindet. Wenn eine Population kleiner wird oder wenn die Überlebens- und Fortpflanzungsraten zwischen den Individuen variieren, kann dies dazu führen, dass bestimmte Gene stärker oder weniger häufig werden. Dies kann dazu führen, dass die Population im Laufe der Zeit unterschiedliche Merkmale aufweist.
|
||||
|
||||
4. Adaptive Radiation: Adaptive Radiation ist ein Prozess, bei dem eine Art mehrere verschiedene Linien auslässt, die sich auf verschiedene Weise an ihre Umgebung anpassen. Dies geschieht normalerweise, wenn die Umwelt sich ändert und die Art neue Fähigkeiten benötigt, um überleben zu können. Die verschiedenen Linien können dann unterschiedliche Eigenschaften entwickeln, die ihnen helfen, in dieser neuen Umgebung zu überleben.
|
||||
```
|
||||
|
||||
## Sachliche Abfrage / RAG
|
||||
|
||||
EM-Modelle bieten ein spezielles Format für RAG (also die Verwendung mit Informationen aus zusätzlichen externen Quellen wie Datenbanken oder Websiten), das für die Minimierung von Halluzinationen und Falscinformationen optimiert ist. Wir verwenden dasselbe Format wie Airoboros dafür.
|
||||
|
||||
### Beispiel
|
||||
|
||||
Prompt
|
||||
```
|
||||
Du bist ein hilfreicher Assistent. Für die folgende Aufgabe stehen dir zwischen den tags BEGININPUT und ENDINPUT mehrere Quellen zur Verfügung. Metadaten zu den einzelnen Quellen wie Autor, URL o.ä. sind zwischen BEGINCONTEXT und ENDCONTEXT zu finden, danach folgt der Text der Quelle. Die eigentliche Aufgabe oder Frage ist zwischen BEGININSTRUCTION und ENDINCSTRUCTION zu finden. Beantworte diese wortwörtlich mit einem Zitat aus den Quellen. Sollten diese keine Antwort enthalten, antworte, dass auf Basis der gegebenen Informationen keine Antwort möglich ist! USER: BEGININPUT
|
||||
BEGINCONTEXT
|
||||
Url: https://www.jph.me
|
||||
ENDCONTEXT
|
||||
Das Wetter in Düsseldorf wird heute schön und sonnig!
|
||||
ENDINPUT
|
||||
BEGININSTRUCTION Was ist 1+1? ENDINSTRUCTION ASSISTANT:
|
||||
```
|
||||
|
||||
Modellantwort:
|
||||
```
|
||||
Mit den gegebenen Informationen ist diese Frage nicht zu beantworten.
|
||||
```
|
||||
|
||||
Hier würde das Modell normalerweise die (triviale) Antwort (2) geben, ist aber trainiert, keine Antwort zu geben, wenn es keine Quelle zwischen BEGININPUT und ENDINPUT gibt, die eine belegbare Antwort liefert.
|
||||
|
||||
Wenn wir anstattdessen fragen:
|
||||
```
|
||||
BEGININSTRUCTION Wie wird das Wetter heute in Düsseldorf? Gebe die Quelle mit an! ENDINSTRUCTION ASSISTANT:
|
||||
```
|
||||
|
||||
Bekommen wir die korrekte Antwort mit Quellenangabe
|
||||
|
||||
```
|
||||
Das Wetter in Düsseldorf wird heute schön und sonnig! (Quelle: Url: https://www.jph.me)
|
||||
```
|
||||
# Evaluation
|
||||
|
||||
coming soon
|
||||
|
||||
# Datensatz
|
||||
|
||||
Der Datensatz ist eine Mischung aus Multi-Turn-Chats, RAG Instructions und synthetisch generierten Finetuning-Daten, die viele Themen und Anwendungen abdecken.
|
||||
|
||||
# Einschränkungen & Vorurteile
|
||||
|
||||
Dieses Modell kann sachlich falsche Ausgaben produzieren und sollte nur zu Forschubngszwecken verwendet werden.
|
||||
|
||||
# Danksagungen:
|
||||
|
||||
Vielen Dank an [winglian/caseus](https://huggingface.co/winglian) für seine großartige Arbeit an Axolotl, die ich zur Schulung der EM-Modelle verwendet habe. Ich bin auch [Jon Durbin](https://huggingface.co/jondurbin) für seine Arioboros Modelle und Code-Schnipsel dankbar, von denen ich viele Ideen nutzen konnte.
|
||||
|
||||
Das 70b-Modell wurde mit Unterstützung des [OVH Cloud Startup Program](https://startup.ovhcloud.com/en/) trainiert.
|
||||
|
||||
# Kontakt
|
||||
|
||||
Wenn Sie an customized LLMs für geschäftliche Anwendungen interessiert sind, kontaktieren Sie mich bitte über [meine Website](https://www.jph.me). Ich freue mich auch immer über Anregungen und Feedback zu meinen Modellen.
|
||||
|
||||
*PS: Ich suche auch immer noch einen Co-Founder für unser Startup, das sich noch im Stealth-Modus befindet.*
|
||||
|
||||
# Haftungsausschluss:
|
||||
|
||||
Ich bin nicht verantwortlich für die Handlungen Dritter, die dieses Modell verwenden. Dieses Modell sollte nur für Forschungszwecke verwendet werden. Die ursprüngliche Llama2-Lizenz gilt und wird mit den Modell-Dateien verteilt.
|
||||
|
||||
50
USE_POLICY.md
Normal file
50
USE_POLICY.md
Normal file
@@ -0,0 +1,50 @@
|
||||
# Llama 2 Acceptable Use Policy
|
||||
|
||||
Meta is committed to promoting safe and fair use of its tools and features, including Llama 2. If you access or use Llama 2, you agree to this Acceptable Use Policy (“Policy”). The most recent copy of this policy can be found at [ai.meta.com/llama/use-policy](http://ai.meta.com/llama/use-policy).
|
||||
|
||||
## Prohibited Uses
|
||||
We want everyone to use Llama 2 safely and responsibly. You agree you will not use, or allow others to use, Llama 2 to:
|
||||
|
||||
1. Violate the law or others’ rights, including to:
|
||||
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
|
||||
1. Violence or terrorism
|
||||
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
|
||||
3. Human trafficking, exploitation, and sexual violence
|
||||
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
|
||||
5. Sexual solicitation
|
||||
6. Any other criminal activity
|
||||
2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
|
||||
3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
|
||||
4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
|
||||
5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws
|
||||
6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama 2 Materials
|
||||
7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
|
||||
|
||||
|
||||
|
||||
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 2 related to the following:
|
||||
1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State
|
||||
2. Guns and illegal weapons (including weapon development)
|
||||
3. Illegal drugs and regulated/controlled substances
|
||||
4. Operation of critical infrastructure, transportation technologies, or heavy machinery
|
||||
5. Self-harm or harm to others, including suicide, cutting, and eating disorders
|
||||
6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
|
||||
|
||||
|
||||
|
||||
3. Intentionally deceive or mislead others, including use of Llama 2 related to the following:
|
||||
1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
|
||||
2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
|
||||
3. Generating, promoting, or further distributing spam
|
||||
4. Impersonating another individual without consent, authorization, or legal right
|
||||
5. Representing that the use of Llama 2 or outputs are human-generated
|
||||
6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
|
||||
4. Fail to appropriately disclose to end users any known dangers of your AI system
|
||||
|
||||
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
|
||||
|
||||
* Reporting issues with the model: [github.com/facebookresearch/llama](http://github.com/facebookresearch/llama)
|
||||
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
|
||||
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
|
||||
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama: [LlamaUseReport@meta.com](mailto:LlamaUseReport@meta.com)
|
||||
|
||||
35
config.json
Normal file
35
config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"_name_or_path": "/workspace/process/jphme_em_german_7b_v01/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,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.34.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000,
|
||||
"quantization_config": {
|
||||
"quant_method": "awq",
|
||||
"zero_point": true,
|
||||
"group_size": 128,
|
||||
"bits": 4,
|
||||
"version": "gemm"
|
||||
}
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 0,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.34.0.dev0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26a2e28d2f70fbde8efb8140ef70d09452e7292e78475e537fe4845afb7d9856
|
||||
size 3889391512
|
||||
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"
|
||||
}
|
||||
5
special_tokens_map.json
Normal file
5
special_tokens_map.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user