初始化项目，由ModelHub XC社区提供模型
Model: TheBloke/NexusRaven-V2-13B-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
|
||||||
41
LICENSE.txt
Normal file
41
LICENSE.txt
Normal file
@@ -0,0 +1,41 @@
|
|||||||
|
Nexusflow.ai License Terms
|
||||||
|
|
||||||
|
NexusRaven-V2 Version Release Date: December 5, 2023
|
||||||
|
|
||||||
|
“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the Nexusflow Materials set forth herein.
|
||||||
|
|
||||||
|
“Documentation” means the specifications, manuals and documentation accompanying NeuxsRaven-V2 distributed by Nexusflow at https://huggingface.co/Nexusflow/NexusRaven-V2-13B, if any.
|
||||||
|
|
||||||
|
“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.
|
||||||
|
|
||||||
|
“NexusRaven-V2” means the 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 made available by Nexusflow at https://huggingface.co/Nexusflow/NexusRaven-V2-13B.
|
||||||
|
|
||||||
|
“Nexusflow Materials” means, collectively, Nexusflow’s proprietary NexusRaven-V2 and Documentation (and any portion thereof) made available under this Agreement.
|
||||||
|
|
||||||
|
“Nexusflow” or “we” means Nexusflow.ai Inc.
|
||||||
|
|
||||||
|
By using or distributing any portion or element of the Nexusflow 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 Nexusflow’s intellectual property or other rights owned by Nexusflow embodied in the Nexusflow Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Nexusflow Materials.
|
||||||
|
b. Redistribution and Use.
|
||||||
|
i. If you distribute or make the Nexusflow 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 Nexusflow Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 1 of this Agreement will not apply to you.
|
||||||
|
iii. You must retain in all copies of the Nexusflow Materials that you distribute the following attribution notice within a “Notice” text file distributed as a part of such copies: “NexusRaven-V2 is licensed under the Nexusflow License, Copyright © Nexusflow.ai Inc. All Rights Reserved.”
|
||||||
|
iv. Your use of the Nexusflow Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to Nexusflow terms and policies (if any), which are hereby incorporated by reference into this Agreement. The Nexusflow Materials are derived from Llama 2 as offered by Meta Platforms Ireland Limited or Meta Platforms, Inc., and you further agree that your use of the Nexusflow Materials shall be subject to the applicable terms and conditions of the Llama 2 Community License Agreement, available at https://ai.meta.com/llama/license/.
|
||||||
|
v. You will not use the Nexusflow Materials or any output or results of the Nexusflow Materials to improve any other large language model (excluding NexusRaven-V2 or derivative works thereof).
|
||||||
|
|
||||||
|
2. Additional Commercial Terms. If, on the NexusRaven-V2 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 50 million monthly active users in the preceding calendar month, you must request a license from Nexusflow, which Nexusflow 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 Nexusflow otherwise expressly grants you such rights.
|
||||||
|
|
||||||
|
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE NEXUSFLOW 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 NEXUSFLOW MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE NEXUSFLOW MATERIALS AND ANY OUTPUT AND RESULTS.
|
||||||
|
|
||||||
|
4. Limitation of Liability. IN NO EVENT WILL NEXUSFLOW, ITS LICENSORS OR 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 NEXUSFLOW 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 Nexusflow Materials, neither Nexusflow 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 using the Nexusflow Materials.
|
||||||
|
b. Subject to Nexusflow’s ownership of Nexusflow Materials and derivatives made by or for Nexusflow (and any rights retained therein by its licensors to the foregoing), with respect to any derivative works and modifications of the Nexusflow Materials that are made by you, as between you and Nexusflow, you are and will be the owner of such derivative works and modifications.
|
||||||
|
c. You will indemnify and hold harmless Nexusflow from and against any claim by any third party arising out of or related to your use of the Nexusflow Materials.
|
||||||
|
|
||||||
|
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Nexusflow Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Nexusflow 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 Nexusflow Materials. Sections 3, 4, 5.c. (the last sentence) 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.
|
||||||
|
|
||||||
578
README.md
Normal file
578
README.md
Normal file
@@ -0,0 +1,578 @@
|
|||||||
|
---
|
||||||
|
base_model: Nexusflow/NexusRaven-V2-13B
|
||||||
|
inference: false
|
||||||
|
license: other
|
||||||
|
model-index:
|
||||||
|
- name: NexusRaven-13B
|
||||||
|
results: []
|
||||||
|
model_creator: Nexusflow
|
||||||
|
model_name: NexusRaven V2 13B
|
||||||
|
model_type: llama
|
||||||
|
prompt_template: "Function:\ndef function_here(arg1):\n \"\"\"\n Comments explaining\
|
||||||
|
\ the function here\n\n Args:\n list args\n\n Returns:\n list returns\n\
|
||||||
|
\ \"\"\"\n\nFunction:\ndef another_function_here(arg1):\n ...\n\nUser Query:\
|
||||||
|
\ {prompt}<human_end>\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 -->
|
||||||
|
|
||||||
|
# NexusRaven V2 13B - GPTQ
|
||||||
|
- Model creator: [Nexusflow](https://huggingface.co/Nexusflow)
|
||||||
|
- Original model: [NexusRaven V2 13B](https://huggingface.co/Nexusflow/NexusRaven-V2-13B)
|
||||||
|
|
||||||
|
<!-- description start -->
|
||||||
|
# Description
|
||||||
|
|
||||||
|
This repo contains GPTQ model files for [Nexusflow's NexusRaven V2 13B](https://huggingface.co/Nexusflow/NexusRaven-V2-13B).
|
||||||
|
|
||||||
|
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/NexusRaven-V2-13B-AWQ)
|
||||||
|
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/NexusRaven-V2-13B-GPTQ)
|
||||||
|
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/NexusRaven-V2-13B-GGUF)
|
||||||
|
* [Nexusflow's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Nexusflow/NexusRaven-V2-13B)
|
||||||
|
<!-- repositories-available end -->
|
||||||
|
|
||||||
|
<!-- prompt-template start -->
|
||||||
|
## Prompt template: NexusRaven
|
||||||
|
|
||||||
|
```
|
||||||
|
Function:
|
||||||
|
def function_here(arg1):
|
||||||
|
"""
|
||||||
|
Comments explaining the function here
|
||||||
|
|
||||||
|
Args:
|
||||||
|
list args
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
list returns
|
||||||
|
"""
|
||||||
|
|
||||||
|
Function:
|
||||||
|
def another_function_here(arg1):
|
||||||
|
...
|
||||||
|
|
||||||
|
User Query: {prompt}<human_end>
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
<!-- prompt-template end -->
|
||||||
|
<!-- licensing start -->
|
||||||
|
## Licensing
|
||||||
|
|
||||||
|
The creator of the source model has listed its license as `other`, and this quantization has therefore used that same license.
|
||||||
|
|
||||||
|
As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.
|
||||||
|
|
||||||
|
In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: [Nexusflow's NexusRaven V2 13B](https://huggingface.co/Nexusflow/NexusRaven-V2-13B).
|
||||||
|
<!-- licensing 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/NexusRaven-V2-13B-GPTQ/tree/main) | 4 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/viewer/) | 8192 | 7.26 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/NexusRaven-V2-13B-GPTQ/tree/gptq-4bit-32g-actorder_True) | 4 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/viewer/) | 8192 | 8.00 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/NexusRaven-V2-13B-GPTQ/tree/gptq-8bit--1g-actorder_True) | 8 | None | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/viewer/) | 8192 | 13.36 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
|
||||||
|
| [gptq-8bit-128g-actorder_True](https://huggingface.co/TheBloke/NexusRaven-V2-13B-GPTQ/tree/gptq-8bit-128g-actorder_True) | 8 | 128 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/viewer/) | 8192 | 13.65 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/NexusRaven-V2-13B-GPTQ/tree/gptq-8bit-32g-actorder_True) | 8 | 32 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/viewer/) | 8192 | 14.55 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
|
||||||
|
| [gptq-4bit-64g-actorder_True](https://huggingface.co/TheBloke/NexusRaven-V2-13B-GPTQ/tree/gptq-4bit-64g-actorder_True) | 4 | 64 | Yes | 0.1 | [Evol Instruct Code](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1/viewer/) | 8192 | 7.51 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/NexusRaven-V2-13B-GPTQ` in the "Download model" box.
|
||||||
|
|
||||||
|
To download from another branch, add `:branchname` to the end of the download name, eg `TheBloke/NexusRaven-V2-13B-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 `NexusRaven-V2-13B-GPTQ`:
|
||||||
|
|
||||||
|
```shell
|
||||||
|
mkdir NexusRaven-V2-13B-GPTQ
|
||||||
|
huggingface-cli download TheBloke/NexusRaven-V2-13B-GPTQ --local-dir NexusRaven-V2-13B-GPTQ --local-dir-use-symlinks False
|
||||||
|
```
|
||||||
|
|
||||||
|
To download from a different branch, add the `--revision` parameter:
|
||||||
|
|
||||||
|
```shell
|
||||||
|
mkdir NexusRaven-V2-13B-GPTQ
|
||||||
|
huggingface-cli download TheBloke/NexusRaven-V2-13B-GPTQ --revision gptq-4bit-32g-actorder_True --local-dir NexusRaven-V2-13B-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 NexusRaven-V2-13B-GPTQ
|
||||||
|
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/NexusRaven-V2-13B-GPTQ --local-dir NexusRaven-V2-13B-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/NexusRaven-V2-13B-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/NexusRaven-V2-13B-GPTQ`.
|
||||||
|
|
||||||
|
- To download from a specific branch, enter for example `TheBloke/NexusRaven-V2-13B-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: `NexusRaven-V2-13B-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/NexusRaven-V2-13B-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'''Function:
|
||||||
|
def function_here(arg1):
|
||||||
|
"""
|
||||||
|
Comments explaining the function here
|
||||||
|
|
||||||
|
Args:
|
||||||
|
list args
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
list returns
|
||||||
|
"""
|
||||||
|
|
||||||
|
Function:
|
||||||
|
def another_function_here(arg1):
|
||||||
|
...
|
||||||
|
|
||||||
|
User Query: {prompt}<human_end>
|
||||||
|
'''
|
||||||
|
|
||||||
|
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/NexusRaven-V2-13B-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 = "Tell me about AI"
|
||||||
|
prompt_template=f'''Function:
|
||||||
|
def function_here(arg1):
|
||||||
|
"""
|
||||||
|
Comments explaining the function here
|
||||||
|
|
||||||
|
Args:
|
||||||
|
list args
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
list returns
|
||||||
|
"""
|
||||||
|
|
||||||
|
Function:
|
||||||
|
def another_function_here(arg1):
|
||||||
|
...
|
||||||
|
|
||||||
|
User Query: {prompt}<human_end>
|
||||||
|
'''
|
||||||
|
|
||||||
|
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 and Mistral models 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: Nexusflow's NexusRaven V2 13B
|
||||||
|
|
||||||
|
# NexusRaven-13B: Surpassing GPT-4 for Zero-shot Function Calling
|
||||||
|
<p align="center">
|
||||||
|
<a href="https://huggingface.co/Nexusflow" target="_blank">Nexusflow HF</a> - <a href="https://discord.gg/HDSVmNAs3y" target="_blank">Nexusflow Discord</a> - <a href="http://nexusflow.ai/blogs/ravenv2" target="_blank">NexusRaven-V2 blog post</a> - <a href="https://colab.research.google.com/drive/19JYixRPPlanmW5q49WYi_tU8rhHeCEKW?usp=sharing" target="_blank">Prompting Notebook CoLab</a> - <a href="https://huggingface.co/spaces/Nexusflow/Nexus_Function_Calling_Leaderboard" target="_blank">Leaderboard</a> - <a href="https://huggingface.co/spaces/Nexusflow/NexusRaven-V2-Demo" target="_blank">Read-World Demo</a> - <a href="https://github.com/nexusflowai/NexusRaven-V2" target="_blank">NexusRaven-V2-13B Github</a>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
<p align="center" width="100%">
|
||||||
|
<a><img src="NexusRaven.png" alt="NexusRaven" style="width: 40%; min-width: 300px; display: block; margin: auto;"></a>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
## Introducing NexusRaven-V2-13B
|
||||||
|
NexusRaven is an open-source and commercially viable function calling LLM that surpasses the state-of-the-art in function calling capabilities.
|
||||||
|
|
||||||
|
💪 **Versatile Function Calling Capability**: NexusRaven-V2 is capable of generating single function calls, nested calls, and parallel calls in many challenging cases.
|
||||||
|
|
||||||
|
🤓 **Fully Explainable**: NexusRaven-V2 is capable of generating very detailed explanations for the function calls it generates. This behavior can be turned off, to save tokens during inference.
|
||||||
|
|
||||||
|
📊 **Performance Highlights**: NexusRaven-V2 surpasses GPT-4 by 7% in function calling success rates in human-generated use cases involving nested and composite functions.
|
||||||
|
|
||||||
|
🔧 **Generalization to the Unseen**: NexusRaven-V2 has never been trained on the functions used in evaluation.
|
||||||
|
|
||||||
|
🔥 **Commercially Permissive**: The training of NexusRaven-V2 does not involve any data generated by proprietary LLMs such as GPT-4. You have full control of the model when deployed in commercial applications.
|
||||||
|
|
||||||
|
Please checkout the following links!
|
||||||
|
- [Prompting Notebook CoLab](https://colab.research.google.com/drive/19JYixRPPlanmW5q49WYi_tU8rhHeCEKW?usp=sharing)
|
||||||
|
- [Evaluation Leaderboard](https://huggingface.co/spaces/Nexusflow/Nexus_Function_Calling_Leaderboard)
|
||||||
|
- [NexusRaven-V2 Real-World Demo](https://huggingface.co/spaces/Nexusflow/NexusRaven-V2-Demo)
|
||||||
|
|
||||||
|
|
||||||
|
## NexusRaven-V2 model usage
|
||||||
|
|
||||||
|
NexusRaven-V2 accepts a list of python functions. These python functions can do anything (including sending GET/POST requests to external APIs!). The two requirements include the python function signature and the appropriate docstring to generate the function call.
|
||||||
|
|
||||||
|
### NexusRaven-V2's Capabilities
|
||||||
|
|
||||||
|
NexusRaven-V2 is capable of generating deeply nested function calls, parallel function calls, and simple single calls. It can also justify the function calls it generated. If you would like to generate the call only, please set a stop criteria of \"\<bot\_end\>\". Otherwise, please allow NexusRaven-V2 to run until its stop token (i.e. "\<\/s\>").
|
||||||
|
|
||||||
|
### Quick Start Prompting Guide
|
||||||
|
|
||||||
|
Please refer to our notebook, [How-To-Prompt.ipynb](https://colab.research.google.com/drive/19JYixRPPlanmW5q49WYi_tU8rhHeCEKW?usp=sharing), for more advanced tutorials on using NexusRaven-V2!
|
||||||
|
|
||||||
|
1. We strongly recommend to set sampling to False when prompting NexusRaven-V2.
|
||||||
|
2. We strongly recommend a very low temperature (~0.001).
|
||||||
|
3. We strongly recommend following the prompting style below.
|
||||||
|
|
||||||
|
### Quickstart
|
||||||
|
You can run the model on a GPU using the following code.
|
||||||
|
```python
|
||||||
|
# Please `pip install transformers accelerate`
|
||||||
|
from transformers import pipeline
|
||||||
|
|
||||||
|
|
||||||
|
pipeline = pipeline(
|
||||||
|
"text-generation",
|
||||||
|
model="Nexusflow/NexusRaven-V2-13B",
|
||||||
|
torch_dtype="auto",
|
||||||
|
device_map="auto",
|
||||||
|
)
|
||||||
|
|
||||||
|
prompt_template = \
|
||||||
|
'''
|
||||||
|
Function:
|
||||||
|
def get_weather_data(coordinates):
|
||||||
|
"""
|
||||||
|
Fetches weather data from the Open-Meteo API for the given latitude and longitude.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
coordinates (tuple): The latitude of the location.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
float: The current temperature in the coordinates you've asked for
|
||||||
|
"""
|
||||||
|
|
||||||
|
Function:
|
||||||
|
def get_coordinates_from_city(city_name):
|
||||||
|
"""
|
||||||
|
Fetches the latitude and longitude of a given city name using the Maps.co Geocoding API.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
city_name (str): The name of the city.
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
tuple: The latitude and longitude of the city.
|
||||||
|
"""
|
||||||
|
|
||||||
|
User Query: {query}<human_end>
|
||||||
|
|
||||||
|
'''
|
||||||
|
|
||||||
|
prompt = prompt_template.format(query="What's the weather like in Seattle right now?")
|
||||||
|
|
||||||
|
result = pipeline(prompt, max_new_tokens=2048, return_full_text=False, do_sample=False, temperature=0.001)[0]["generated_text"]
|
||||||
|
print (result)
|
||||||
|
```
|
||||||
|
|
||||||
|
This should generate the following:
|
||||||
|
```
|
||||||
|
Call: get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))<bot_end>
|
||||||
|
Thought: The function call `get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))` answers the question "What's the weather like in Seattle right now?" by following these steps:
|
||||||
|
|
||||||
|
1. `get_coordinates_from_city(city_name='Seattle')`: This function call fetches the latitude and longitude of the city "Seattle" using the Maps.co Geocoding API.
|
||||||
|
2. `get_weather_data(coordinates=...)`: This function call fetches the current weather data for the coordinates returned by the previous function call.
|
||||||
|
|
||||||
|
Therefore, the function call `get_weather_data(coordinates=get_coordinates_from_city(city_name='Seattle'))` answers the question "What's the weather like in Seattle right now?" by first fetching the coordinates of the city "Seattle" and then fetching the current weather data for those coordinates.
|
||||||
|
```
|
||||||
|
|
||||||
|
If you would like to prevent the generation of the explanation of the function call (for example, to save on inference tokens), please set a stopping criteria of \<bot_end\>.
|
||||||
|
|
||||||
|
Please follow this prompting template to maximize the performance of RavenV2.
|
||||||
|
|
||||||
|
### Using with OpenAI FC Schematics
|
||||||
|
|
||||||
|
[If you currently have a workflow that is built around OpenAI's function calling and you want to try NexusRaven-V2, we have a package that helps you drop in NexusRaven-V2.](https://github.com/nexusflowai/nexusraven-pip)
|
||||||
|
|
||||||
|
|
||||||
|
## Evaluation
|
||||||
|
|
||||||
|
<p align="center" width="100%">
|
||||||
|
<a><img src="blog2-fc.png" alt="NexusRaven" style="width: 80%; min-width: 300px; display: block; margin: auto;"></a>
|
||||||
|
<a><img src="radar-2.png" alt="NexusRaven" style="width: 80%; min-width: 300px; display: block; margin: auto;"></a>
|
||||||
|
</p>
|
||||||
|
|
||||||
|
For a deeper dive into the results, please see our [Github README](https://github.com/nexusflowai/NexusRaven).
|
||||||
|
|
||||||
|
# Limitations
|
||||||
|
1. The model works best when it is connected with a retriever when there are a multitude of functions, as a large number of functions will saturate the context window of this model.
|
||||||
|
2. The model can be prone to generate incorrect calls. Please ensure proper guardrails to capture errant behavior is in place.
|
||||||
|
3. The explanations generated by NexusRaven-V2 might be incorrect. Please ensure proper guardrails are present to capture errant behavior.
|
||||||
|
|
||||||
|
## License
|
||||||
|
This model was trained on commercially viable data and is licensed under the [Nexusflow community license](https://huggingface.co/Nexusflow/NexusRaven-V2-13B/blob/main/LICENSE.txt).
|
||||||
|
|
||||||
|
|
||||||
|
## References
|
||||||
|
We thank the CodeLlama team for their amazing models!
|
||||||
|
|
||||||
|
```
|
||||||
|
@misc{rozière2023code,
|
||||||
|
title={Code Llama: Open Foundation Models for Code},
|
||||||
|
author={Baptiste Rozière and Jonas Gehring and Fabian Gloeckle and Sten Sootla and Itai Gat and Xiaoqing Ellen Tan and Yossi Adi and Jingyu Liu and Tal Remez and Jérémy Rapin and Artyom Kozhevnikov and Ivan Evtimov and Joanna Bitton and Manish Bhatt and Cristian Canton Ferrer and Aaron Grattafiori and Wenhan Xiong and Alexandre Défossez and Jade Copet and Faisal Azhar and Hugo Touvron and Louis Martin and Nicolas Usunier and Thomas Scialom and Gabriel Synnaeve},
|
||||||
|
year={2023},
|
||||||
|
eprint={2308.12950},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
## Citation
|
||||||
|
```
|
||||||
|
@misc{nexusraven,
|
||||||
|
title={NexusRaven-V2: Surpassing GPT-4 for Zero-shot Function Calling},
|
||||||
|
author={Nexusflow.ai team},
|
||||||
|
year={2023},
|
||||||
|
url={https://nexusflow.ai/blogs/ravenv2}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
## Contact
|
||||||
|
Please join our [Discord Channel](https://discord.gg/HDSVmNAs3y) to reach out for any issues and comments!
|
||||||
10
added_tokens.json
Normal file
10
added_tokens.json
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
{
|
||||||
|
"<bot>:": 32017,
|
||||||
|
"<bot_end>": 32019,
|
||||||
|
"<docstring_end>": 32023,
|
||||||
|
"<docstring_start>": 32022,
|
||||||
|
"<func_end>": 32021,
|
||||||
|
"<func_start>": 32020,
|
||||||
|
"<human>:": 32016,
|
||||||
|
"<human_end>": 32018
|
||||||
|
}
|
||||||
40
config.json
Normal file
40
config.json
Normal file
@@ -0,0 +1,40 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/workspace/process/nexusflow_nexusraven-v2-13b/source",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 13824,
|
||||||
|
"low_cpu_mem_usage": false,
|
||||||
|
"max_position_embeddings": 16384,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 40,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 40,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.35.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32024,
|
||||||
|
"quantization_config": {
|
||||||
|
"bits": 4,
|
||||||
|
"group_size": 128,
|
||||||
|
"damp_percent": 0.1,
|
||||||
|
"desc_act": true,
|
||||||
|
"sym": true,
|
||||||
|
"true_sequential": true,
|
||||||
|
"model_name_or_path": null,
|
||||||
|
"model_file_base_name": "model",
|
||||||
|
"quant_method": "gptq"
|
||||||
|
}
|
||||||
|
}
|
||||||
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": "4.33.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8080380972cb8f5aad4540122dcbfd98cad55000c5536c5b582daa8df00ab6d9
|
||||||
|
size 7259926800
|
||||||
10
quantize_config.json
Normal file
10
quantize_config.json
Normal file
@@ -0,0 +1,10 @@
|
|||||||
|
{
|
||||||
|
"bits": 4,
|
||||||
|
"group_size": 128,
|
||||||
|
"damp_percent": 0.1,
|
||||||
|
"desc_act": true,
|
||||||
|
"sym": true,
|
||||||
|
"true_sequential": true,
|
||||||
|
"model_name_or_path": null,
|
||||||
|
"model_file_base_name": "model"
|
||||||
|
}
|
||||||
34
special_tokens_map.json
Normal file
34
special_tokens_map.json
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<human>:",
|
||||||
|
"<bot>:",
|
||||||
|
"<human_end>",
|
||||||
|
"<bot_end>",
|
||||||
|
"<func_start>",
|
||||||
|
"<func_end>",
|
||||||
|
"<docstring_start>",
|
||||||
|
"<docstring_end>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "</s>",
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
93526
tokenizer.json
Normal file
93526
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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
||||||
|
size 500058
|
||||||
45
tokenizer_config.json
Normal file
45
tokenizer_config.json
Normal file
@@ -0,0 +1,45 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"▁<PRE>",
|
||||||
|
"▁<MID>",
|
||||||
|
"▁<SUF>",
|
||||||
|
"▁<EOT>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eot_token": "▁<EOT>",
|
||||||
|
"fill_token": "<FILL_ME>",
|
||||||
|
"legacy": null,
|
||||||
|
"middle_token": "▁<MID>",
|
||||||
|
"model_max_length": 8192,
|
||||||
|
"pad_token": null,
|
||||||
|
"prefix_token": "▁<PRE>",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"suffix_token": "▁<SUF>",
|
||||||
|
"tokenizer_class": "CodeLlamaTokenizer",
|
||||||
|
"truncation_side": "left",
|
||||||
|
"unk_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"use_default_system_prompt": false
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user