初始化项目，由ModelHub XC社区提供模型
Model: TheBloke/Sensei-7B-V1-GPTQ 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
|
||||
94
LICENSE
Normal file
94
LICENSE
Normal file
@@ -0,0 +1,94 @@
|
||||
Business Source License 1.1
|
||||
|
||||
License text copyright (c) 2017 MariaDB Corporation Ab, All Rights Reserved.
|
||||
"Business Source License" is a trademark of MariaDB Corporation Ab.
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
|
||||
Parameters
|
||||
|
||||
Licensor: Emergent AGI Inc.
|
||||
|
||||
Licensed Work: SciPhi/Sensei-7B-V1
|
||||
The Licensed Work is (c) 2023 SciPhi
|
||||
|
||||
Change License: GNU General Public License v2.0 or later
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
|
||||
Terms
|
||||
|
||||
The Licensor hereby grants you the right to copy, modify, create derivative
|
||||
works, redistribute, and make non-production use of the Licensed Work. The
|
||||
Licensor may make an Additional Use Grant, above, permitting limited
|
||||
production use.
|
||||
|
||||
Effective on the Change Date, or the fourth anniversary of the first publicly
|
||||
available distribution of a specific version of the Licensed Work under this
|
||||
License, whichever comes first, the Licensor hereby grants you rights under
|
||||
the terms of the Change License, and the rights granted in the paragraph
|
||||
above terminate.
|
||||
|
||||
If your use of the Licensed Work does not comply with the requirements
|
||||
currently in effect as described in this License, you must purchase a
|
||||
commercial license from the Licensor, its affiliated entities, or authorized
|
||||
resellers, or you must refrain from using the Licensed Work.
|
||||
|
||||
All copies of the original and modified Licensed Work, and derivative works
|
||||
of the Licensed Work, are subject to this License. This License applies
|
||||
separately for each version of the Licensed Work and the Change Date may vary
|
||||
for each version of the Licensed Work released by Licensor.
|
||||
|
||||
You must conspicuously display this License on each original or modified copy
|
||||
of the Licensed Work. If you receive the Licensed Work in original or
|
||||
modified form from a third party, the terms and conditions set forth in this
|
||||
License apply to your use of that work.
|
||||
|
||||
Any use of the Licensed Work in violation of this License will automatically
|
||||
terminate your rights under this License for the current and all other
|
||||
versions of the Licensed Work.
|
||||
|
||||
This License does not grant you any right in any trademark or logo of
|
||||
Licensor or its affiliates (provided that you may use a trademark or logo of
|
||||
Licensor as expressly required by this License).
|
||||
|
||||
TO THE EXTENT PERMITTED BY APPLICABLE LAW, THE LICENSED WORK IS PROVIDED ON
|
||||
AN "AS IS" BASIS. LICENSOR HEREBY DISCLAIMS ALL WARRANTIES AND CONDITIONS,
|
||||
EXPRESS OR IMPLIED, INCLUDING (WITHOUT LIMITATION) WARRANTIES OF
|
||||
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, NON-INFRINGEMENT, AND
|
||||
TITLE.
|
||||
|
||||
MariaDB hereby grants you permission to use this License’s text to license
|
||||
your works, and to refer to it using the trademark "Business Source License",
|
||||
as long as you comply with the Covenants of Licensor below.
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
|
||||
Covenants of Licensor
|
||||
|
||||
In consideration of the right to use this License’s text and the "Business
|
||||
Source License" name and trademark, Licensor covenants to MariaDB, and to all
|
||||
other recipients of the licensed work to be provided by Licensor:
|
||||
|
||||
1. To specify as the Change License the GPL Version 2.0 or any later version,
|
||||
or a license that is compatible with GPL Version 2.0 or a later version,
|
||||
where "compatible" means that software provided under the Change License can
|
||||
be included in a program with software provided under GPL Version 2.0 or a
|
||||
later version. Licensor may specify additional Change Licenses without
|
||||
limitation.
|
||||
|
||||
2. To either: (a) specify an additional grant of rights to use that does not
|
||||
impose any additional restriction on the right granted in this License, as
|
||||
the Additional Use Grant; or (b) insert the text "None".
|
||||
|
||||
3. To specify a Change Date.
|
||||
|
||||
4. Not to modify this License in any other way.
|
||||
|
||||
-----------------------------------------------------------------------------
|
||||
|
||||
Notice
|
||||
|
||||
The Business Source License (this document, or the "License") is not an Open
|
||||
Source license. However, the Licensed Work will eventually be made available
|
||||
under an Open Source License, as stated in this License.
|
||||
456
README.md
Normal file
456
README.md
Normal file
@@ -0,0 +1,456 @@
|
||||
---
|
||||
base_model: SciPhi/Sensei-7B-V1
|
||||
inference: false
|
||||
model_creator: SciPhi-AI
|
||||
model_name: Sensei 7B v1
|
||||
model_type: mistral
|
||||
prompt_template: "### Instruction: \nYour task is to perform retrieval augmented generation\
|
||||
\ (RAG) over the given query and search results. Return your answer in a json format\
|
||||
\ that includes a summary of the search results and a list of related queries. \n\
|
||||
\nQuery:\n{prompt}\n\\n\\n\nSearch Results:\n{{context}}\n\\n\\n\nQuery:\n{prompt}\n\
|
||||
\n### Response:\n{{\"summary\":\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 -->
|
||||
|
||||
# Sensei 7B v1 - GPTQ
|
||||
- Model creator: [SciPhi-AI](https://huggingface.co/SciPhi)
|
||||
- Original model: [Sensei 7B v1](https://huggingface.co/SciPhi/Sensei-7B-V1)
|
||||
|
||||
<!-- description start -->
|
||||
# Description
|
||||
|
||||
This repo contains GPTQ model files for [SciPhi-AI's Sensei 7B v1](https://huggingface.co/SciPhi/Sensei-7B-V1).
|
||||
|
||||
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
|
||||
|
||||
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
|
||||
|
||||
<!-- description end -->
|
||||
<!-- repositories-available start -->
|
||||
## Repositories available
|
||||
|
||||
* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Sensei-7B-V1-AWQ)
|
||||
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ)
|
||||
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Sensei-7B-V1-GGUF)
|
||||
* [SciPhi-AI's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/SciPhi/Sensei-7B-V1)
|
||||
<!-- repositories-available end -->
|
||||
|
||||
<!-- prompt-template start -->
|
||||
## Prompt template: Sensei-RAG
|
||||
|
||||
```
|
||||
### Instruction:
|
||||
Your task is to perform retrieval augmented generation (RAG) over the given query and search results. Return your answer in a json format that includes a summary of the search results and a list of related queries.
|
||||
|
||||
Query:
|
||||
{prompt}
|
||||
\n\n
|
||||
Search Results:
|
||||
{{context}}
|
||||
\n\n
|
||||
Query:
|
||||
{prompt}
|
||||
|
||||
### Response:
|
||||
{{"summary":
|
||||
|
||||
```
|
||||
|
||||
<!-- prompt-template end -->
|
||||
|
||||
|
||||
|
||||
<!-- README_GPTQ.md-compatible clients start -->
|
||||
## Known compatible clients / servers
|
||||
|
||||
GPTQ models are currently supported on Linux (NVidia/AMD) and Windows (NVidia only). macOS users: please use GGUF models.
|
||||
|
||||
These GPTQ models are known to work in the following inference servers/webuis.
|
||||
|
||||
- [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
|
||||
- [KoboldAI United](https://github.com/henk717/koboldai)
|
||||
- [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
|
||||
- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
|
||||
|
||||
This may not be a complete list; if you know of others, please let me know!
|
||||
<!-- README_GPTQ.md-compatible clients end -->
|
||||
|
||||
<!-- README_GPTQ.md-provided-files start -->
|
||||
## Provided files, and GPTQ parameters
|
||||
|
||||
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
|
||||
|
||||
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
|
||||
|
||||
Most GPTQ files are made with AutoGPTQ. Mistral models are currently made with Transformers.
|
||||
|
||||
<details>
|
||||
<summary>Explanation of GPTQ parameters</summary>
|
||||
|
||||
- Bits: The bit size of the quantised model.
|
||||
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
|
||||
- Act Order: True or False. Also known as `desc_act`. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now.
|
||||
- Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
|
||||
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
|
||||
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
|
||||
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama and Mistral models in 4-bit.
|
||||
|
||||
</details>
|
||||
|
||||
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
|
||||
| ------ | ---- | -- | --------- | ------ | ------------ | ------- | ---- | ------- | ---- |
|
||||
| [main](https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.16 GB | Yes | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
|
||||
| [gptq-4bit-32g-actorder_True](https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.57 GB | Yes | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
|
||||
| [gptq-8bit--1g-actorder_True](https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 7.52 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
|
||||
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 7.68 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
|
||||
| [gptq-8bit-32g-actorder_True](https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 8.17 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
|
||||
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.29 GB | Yes | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
|
||||
|
||||
<!-- README_GPTQ.md-provided-files end -->
|
||||
|
||||
<!-- README_GPTQ.md-download-from-branches start -->
|
||||
## How to download, including from branches
|
||||
|
||||
### In text-generation-webui
|
||||
|
||||
To download from the `main` branch, enter `TheBloke/Sensei-7B-V1-GPTQ` in the "Download model" box.
|
||||
|
||||
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/Sensei-7B-V1-GPTQ:gptq-4bit-32g-actorder_True`
|
||||
|
||||
### From the command line
|
||||
|
||||
I recommend using the `huggingface-hub` Python library:
|
||||
|
||||
```shell
|
||||
pip3 install huggingface-hub
|
||||
```
|
||||
|
||||
To download the `main` branch to a folder called `Sensei-7B-V1-GPTQ`:
|
||||
|
||||
```shell
|
||||
mkdir Sensei-7B-V1-GPTQ
|
||||
huggingface-cli download TheBloke/Sensei-7B-V1-GPTQ --local-dir Sensei-7B-V1-GPTQ --local-dir-use-symlinks False
|
||||
```
|
||||
|
||||
To download from a different branch, add the `--revision` parameter:
|
||||
|
||||
```shell
|
||||
mkdir Sensei-7B-V1-GPTQ
|
||||
huggingface-cli download TheBloke/Sensei-7B-V1-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir Sensei-7B-V1-GPTQ --local-dir-use-symlinks False
|
||||
```
|
||||
|
||||
<details>
|
||||
<summary>More advanced huggingface-cli download usage</summary>
|
||||
|
||||
If you remove the `--local-dir-use-symlinks False` parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: `~/.cache/huggingface`), and symlinks will be added to the specified `--local-dir`, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
|
||||
|
||||
The cache location can be changed with the `HF_HOME` environment variable, and/or the `--cache-dir` parameter to `huggingface-cli`.
|
||||
|
||||
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
|
||||
|
||||
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
|
||||
|
||||
```shell
|
||||
pip3 install hf_transfer
|
||||
```
|
||||
|
||||
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
|
||||
|
||||
```shell
|
||||
mkdir Sensei-7B-V1-GPTQ
|
||||
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Sensei-7B-V1-GPTQ --local-dir Sensei-7B-V1-GPTQ --local-dir-use-symlinks False
|
||||
```
|
||||
|
||||
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
|
||||
</details>
|
||||
|
||||
### With `git` (**not** recommended)
|
||||
|
||||
To clone a specific branch with `git`, use a command like this:
|
||||
|
||||
```shell
|
||||
git clone --single-branch --branch gptq-4bit-32g-actorder_True https://huggingface.co/TheBloke/Sensei-7B-V1-GPTQ
|
||||
```
|
||||
|
||||
Note that using Git with HF repos is strongly discouraged. It will be much slower than using `huggingface-hub`, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the `.git` folder as a blob.)
|
||||
|
||||
<!-- README_GPTQ.md-download-from-branches end -->
|
||||
<!-- README_GPTQ.md-text-generation-webui start -->
|
||||
## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
|
||||
|
||||
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/Sensei-7B-V1-GPTQ`.
|
||||
|
||||
- To download from a specific branch, enter for example `TheBloke/Sensei-7B-V1-GPTQ:gptq-4bit-32g-actorder_True`
|
||||
- see Provided Files above for the list of branches for each option.
|
||||
|
||||
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: `Sensei-7B-V1-GPTQ`
|
||||
7. The model will automatically load, and is now ready for use!
|
||||
8. 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.
|
||||
|
||||
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file `quantize_config.json`.
|
||||
|
||||
9. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
|
||||
|
||||
<!-- README_GPTQ.md-text-generation-webui end -->
|
||||
|
||||
<!-- README_GPTQ.md-use-from-tgi start -->
|
||||
## Serving this model from Text Generation Inference (TGI)
|
||||
|
||||
It's recommended to 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/Sensei-7B-V1-GPTQ --port 3000 --quantize gptq --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'''### Instruction:
|
||||
Your task is to perform retrieval augmented generation (RAG) over the given query and search results. Return your answer in a json format that includes a summary of the search results and a list of related queries.
|
||||
|
||||
Query:
|
||||
{prompt}
|
||||
\n\n
|
||||
Search Results:
|
||||
{{context}}
|
||||
\n\n
|
||||
Query:
|
||||
{prompt}
|
||||
|
||||
### Response:
|
||||
{{"summary":
|
||||
'''
|
||||
|
||||
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_GPTQ.md-use-from-tgi end -->
|
||||
<!-- README_GPTQ.md-use-from-python start -->
|
||||
## Python code example: inference from this GPTQ model
|
||||
|
||||
### Install the necessary packages
|
||||
|
||||
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
|
||||
|
||||
```shell
|
||||
pip3 install --upgrade transformers optimum
|
||||
# If using PyTorch 2.1 + CUDA 12.x:
|
||||
pip3 install --upgrade auto-gptq
|
||||
# or, if using PyTorch 2.1 + CUDA 11.x:
|
||||
pip3 install --upgrade auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
|
||||
```
|
||||
|
||||
If you are using PyTorch 2.0, you will need to install AutoGPTQ from source. Likewise if you have problems with the pre-built wheels, you should try building from source:
|
||||
|
||||
```shell
|
||||
pip3 uninstall -y auto-gptq
|
||||
git clone https://github.com/PanQiWei/AutoGPTQ
|
||||
cd AutoGPTQ
|
||||
git checkout v0.5.1
|
||||
pip3 install .
|
||||
```
|
||||
|
||||
### Example Python code
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
|
||||
|
||||
model_name_or_path = "TheBloke/Sensei-7B-V1-GPTQ"
|
||||
# To use a different branch, change revision
|
||||
# For example: revision="gptq-4bit-32g-actorder_True"
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
|
||||
device_map="auto",
|
||||
trust_remote_code=False,
|
||||
revision="main")
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
|
||||
|
||||
prompt = "Write a story about llamas"
|
||||
system_message = "You are a story writing assistant"
|
||||
prompt_template=f'''### Instruction:
|
||||
Your task is to perform retrieval augmented generation (RAG) over the given query and search results. Return your answer in a json format that includes a summary of the search results and a list of related queries.
|
||||
|
||||
Query:
|
||||
{prompt}
|
||||
\n\n
|
||||
Search Results:
|
||||
{{context}}
|
||||
\n\n
|
||||
Query:
|
||||
{prompt}
|
||||
|
||||
### Response:
|
||||
{{"summary":
|
||||
'''
|
||||
|
||||
print("\n\n*** Generate:")
|
||||
|
||||
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
|
||||
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
|
||||
print(tokenizer.decode(output[0]))
|
||||
|
||||
# Inference can also be done using transformers' 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_GPTQ.md-use-from-python end -->
|
||||
|
||||
<!-- README_GPTQ.md-compatibility start -->
|
||||
## Compatibility
|
||||
|
||||
The files provided are tested to work with Transformers. For non-Mistral models, AutoGPTQ can also be used directly.
|
||||
|
||||
[ExLlama](https://github.com/turboderp/exllama) is compatible with Llama architecture models (including Mistral, Yi, DeepSeek, SOLAR, etc) in 4-bit. Please see the Provided Files table above for per-file compatibility.
|
||||
|
||||
For a list of clients/servers, please see "Known compatible clients / servers", above.
|
||||
<!-- README_GPTQ.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: SciPhi-AI's Sensei 7B v1
|
||||
|
||||
|
||||
# Sensei-7B-V1 Model Card
|
||||
|
||||
Sensei-7B-V1 is a Large Language Model (LLM) fine-tuned from OpenPipe's mistral-ft-optimized-1218, which is based on Mistral-7B. Sensei-7B-V1 was was fine-tuned with a fully synthetic dataset to specialize at performing retrieval-augmented generation (RAG) over detailed web search results. This model strives to specialize in using search, such as [AgentSearch](https://huggingface.co/datasets/SciPhi/AgentSearch-V1), to generate accurate and well-cited summaries from a range of search results, providing more accurate answers to user queries. Please refer to the [docs here](https://agent-search.readthedocs.io/en/latest/) for more information on how to run Sensei end-to-end.
|
||||
|
||||
Currently, Sensei is available via hosted api at https://www.sciphi.ai. You can try a demonstration [here](https://search.sciphi.ai/).
|
||||
|
||||
## Model Architecture
|
||||
|
||||
Base Model: mistral-ft-optimized-1218
|
||||
|
||||
**Architecture Features:**
|
||||
- Transformer-based model
|
||||
- Grouped-Query Attention
|
||||
- Sliding-Window Attention
|
||||
- Byte-fallback BPE tokenizer
|
||||
|
||||
|
||||
## Using the Model
|
||||
|
||||
It is recommended to use a single search query. The model will return an answer using search results as context.
|
||||
|
||||
Using the AgentSearch package an example is shown below.
|
||||
```
|
||||
export SCIPHI_API_KEY=MY_SCIPHI_API_KEY
|
||||
# Use `Sensei` for LLM RAG w/ AgentSearch
|
||||
python -m agent_search.scripts.run_rag run --query="What is Fermat's last theorem?"
|
||||
```
|
||||
|
||||
Alternatively, you may provide your own search context directly to the model by adhereing to the following format:
|
||||
|
||||
```
|
||||
### Instruction:
|
||||
Your task is to perform retrieval augmented generation (RAG) over the given query and search results. Return your answer in a json format that includes a summary of the search results and a list of related queries.
|
||||
|
||||
Query:
|
||||
{prompt}
|
||||
\n\n
|
||||
Search Results:
|
||||
{context}
|
||||
\n\n
|
||||
Query:
|
||||
{prompt}
|
||||
|
||||
### Response:
|
||||
{"summary":
|
||||
```
|
||||
|
||||
__Note__: The inclusion of the text '{"summary":' following the Response footer is intentional. This ensures that the model responds with the proper json format, failure to include this leading prefix can cause small deviaitons. Combining the output with the leading string '{"summary":' results in a properly formatted JSON with keys 'summary' and 'other_queries'.
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
||||
|
||||
## References
|
||||
|
||||
1. OpenPipe AI. (2023). Model Card for mistral-ft-optimized-1218. The mistral-ft-1218 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters optimized for downstream fine-tuning on a variety of tasks. For full details, please refer to the release blog post. Model Architecture: Transformer with Grouped-Query Attention, Sliding-Window Attention, and Byte-fallback BPE tokenizer. [Link](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
|
||||
57
config.json
Normal file
57
config.json
Normal file
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"_name_or_path": "/workspace/process/sciphi_sensei-7b-v1/source",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 4096,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000,
|
||||
"quantization_config": {
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"damp_percent": 0.1,
|
||||
"desc_act": true,
|
||||
"static_groups": false,
|
||||
"sym": true,
|
||||
"true_sequential": true,
|
||||
"model_name_or_path": null,
|
||||
"model_file_base_name": "model",
|
||||
"quant_method": "gptq",
|
||||
"modules_in_block_to_quantize": [
|
||||
[
|
||||
"self_attn.k_proj",
|
||||
"self_attn.v_proj",
|
||||
"self_attn.q_proj"
|
||||
],
|
||||
[
|
||||
"self_attn.o_proj"
|
||||
],
|
||||
[
|
||||
"mlp.up_proj",
|
||||
"mlp.gate_proj"
|
||||
],
|
||||
[
|
||||
"mlp.down_proj"
|
||||
]
|
||||
]
|
||||
}
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.36.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd5feb240875cf7954f7fb76ef3d9d90dd16aa7e2b1fe47ff1af3fa4ecfc1206
|
||||
size 4158662280
|
||||
11
quantize_config.json
Normal file
11
quantize_config.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"bits": 4,
|
||||
"group_size": 128,
|
||||
"damp_percent": 0.1,
|
||||
"desc_act": true,
|
||||
"static_groups": false,
|
||||
"sym": true,
|
||||
"true_sequential": true,
|
||||
"model_name_or_path": null,
|
||||
"model_file_base_name": "model"
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "</s>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
44
tokenizer_config.json
Normal file
44
tokenizer_config.json
Normal file
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"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": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"trust_remote_code": true,
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user