It is the result of first merging the deltas from the above repository with the original Llama 13B weights, then quantising to 4bit using GPTQ-for-LLaMa.
In the main branch - the default one - you will find stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors
This will work with all versions of GPTQ-for-LLaMa. It has maximum compatibility
It was created without the --act-order parameter. It may have slightly lower inference quality compared to the other file, but is guaranteed to work on all versions of GPTQ-for-LLaMa and text-generation-webui.
File stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors can be loaded the same as any other GPTQ file, without requiring any updates to oobaboogas text-generation-webui.
The other safetensors model file was created using --act-order to give the maximum possible quantisation quality, but this means it requires that the latest GPTQ-for-LLaMa is used inside the UI.
If you want to use the act-order safetensors files and need to update the Triton branch of GPTQ-for-LLaMa, here are the commands I used to clone the Triton branch of GPTQ-for-LLaMa, clone text-generation-webui, and install GPTQ into the UI:
# Clone text-generation-webui, if you don't already have it
git clone https://github.com/oobabooga/text-generation-webui
# Make a repositories directory
mkdir text-generation-webui/repositories
cd text-generation-webui/repositories
# Clone the latest GPTQ-for-LLaMa code inside text-generation-webui
git clone https://github.com/qwopqwop200/GPTQ-for-LLaMa
Then install this model into text-generation-webui/models and launch the UI as follows:
cd text-generation-webui
python server.py --model stable-vicuna-13B-GPTQ --wbits 4 --groupsize 128 --model_type Llama # add any other command line args you want
The above commands assume you have installed all dependencies for GPTQ-for-LLaMa and text-generation-webui. Please see their respective repositories for further information.
If you can't update GPTQ-for-LLaMa or don't want to, you can use stable-vicuna-13B-GPTQ-4bit.no-act-order.safetensors as mentioned above, which should work without any upgrades to text-generation-webui.
Discord
For further support, and discussions on these models and AI in general, join us at:
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 special mentions: Sam, theTransient, Jonathan Leane, Steven Wood, webtim, Johann-Peter Hartmann, Geoffrey Montalvo, Gabriel Tamborski, Willem Michiel, John Villwock, Derek Yates, Mesiah Bishop, Eugene Pentland, Pieter, Chadd, Stephen Murray, Daniel P. Andersen, terasurfer, Brandon Frisco, Thomas Belote, Sid, Nathan LeClaire, Magnesian, Alps Aficionado, Stanislav Ovsiannikov, Alex, Joseph William Delisle, Nikolai Manek, Michael Davis, Junyu Yang, K, J, Spencer Kim, Stefan Sabev, Olusegun Samson, transmissions 11, Michael Levine, Cory Kujawski, Rainer Wilmers, zynix, Kalila, Luke @flexchar, Ajan Kanaga, Mandus, vamX, Ai Maven, Mano Prime, Matthew Berman, subjectnull, Vitor Caleffi, Clay Pascal, biorpg, alfie_i, 阿明, Jeffrey Morgan, ya boyyy, Raymond Fosdick, knownsqashed, Olakabola, Leonard Tan, ReadyPlayerEmma, Enrico Ros, Dave, Talal Aujan, Illia Dulskyi, Sean Connelly, senxiiz, Artur Olbinski, Elle, Raven Klaugh, Fen Risland, Deep Realms, Imad Khwaja, Fred von Graf, Will Dee, usrbinkat, SuperWojo, Alexandros Triantafyllidis, Swaroop Kallakuri, Dan Guido, John Detwiler, Pedro Madruga, Iucharbius, Viktor Bowallius, Asp the Wyvern, Edmond Seymore, Trenton Dambrowitz, Space Cruiser, Spiking Neurons AB, Pyrater, LangChain4j, Tony Hughes, Kacper Wikieł, Rishabh Srivastava, David Ziegler, Luke Pendergrass, Andrey, Gabriel Puliatti, Lone Striker, Sebastain Graf, Pierre Kircher, Randy H, NimbleBox.ai, Vadim, danny, Deo Leter
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original StableVicuna-13B model card
Model Description
StableVicuna-13B is a Vicuna-13B v0 model fine-tuned using reinforcement learning from human feedback (RLHF) via Proximal Policy Optimization (PPO) on various conversational and instructional datasets.
Contact: For questions and comments about the model, visit the CarperAI and StableFoundation Discord servers.
Hyperparameter
Value
\(n_\text{parameters}\)
13B
\(d_\text{model}\)
5120
\(n_\text{layers}\)
40
\(n_\text{heads}\)
40
Training
Training Dataset
StableVicuna-13B is fine-tuned on a mix of three datasets. OpenAssistant Conversations Dataset (OASST1), a human-generated, human-annotated assistant-style conversation corpus consisting of 161,443 messages distributed across 66,497 conversation trees, in 35 different languages;
GPT4All Prompt Generations, a dataset of 400k prompts and responses generated by GPT-4; and Alpaca, a dataset of 52,000 instructions and demonstrations generated by OpenAI's text-davinci-003 engine.
The reward model used during RLHF was also trained on OpenAssistant Conversations Dataset (OASST1) along with two other datasets: Anthropic HH-RLHF, a dataset of preferences about AI assistant helpfulness and harmlessness; and Stanford Human Preferences Dataset a dataset of 385K collective human preferences over responses to questions/instructions in 18 different subject areas, from cooking to legal advice.
Training Procedure
CarperAI/stable-vicuna-13b-delta was trained using PPO as implemented in trlX with the following configuration:
Hyperparameter
Value
num_rollouts
128
chunk_size
16
ppo_epochs
4
init_kl_coef
0.1
target
6
horizon
10000
gamma
1
lam
0.95
cliprange
0.2
cliprange_value
0.2
vf_coef
1.0
scale_reward
None
cliprange_reward
10
generation_kwargs
max_length
512
min_length
48
top_k
0.0
top_p
1.0
do_sample
True
temperature
1.0
Use and Limitations
Intended Use
This model is intended to be used for text generation with a focus on conversational tasks. Users may further fine-tune the model on their own data to improve the model's performance on their specific tasks in accordance with the non-commercial license.
Limitations and bias
The base LLaMA model is trained on various data, some of which may contain offensive, harmful, and biased content that can lead to toxic behavior. See Section 5.1 of the LLaMA paper. We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity. Do not treat chat responses from this model as a substitute for human judgment or as a source of truth. Please use responsibly.
Acknowledgements
This work would not have been possible without the support of Stability AI.
Citations
bibtex
1@article{touvron2023llama,
2 title={LLaMA: Open and Efficient Foundation Language Models},
3 author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
4 journal={arXiv preprint arXiv:2302.13971},
5 year={2023}
6}
bibtex
1@misc{vicuna2023,
2 title = {Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality},
3 url = {https://vicuna.lmsys.org},
4 author = {Chiang, Wei-Lin and Li, Zhuohan and Lin, Zi and Sheng, Ying and Wu, Zhanghao and Zhang, Hao and Zheng, Lianmin and Zhuang, Siyuan and Zhuang, Yonghao and Gonzalez, Joseph E. and Stoica, Ion and Xing, Eric P.},
5 month = {March},
6 year = {2023}
7}
bibtex
1@misc{gpt4all,
2 author = {Yuvanesh Anand and Zach Nussbaum and Brandon Duderstadt and Benjamin Schmidt and Andriy Mulyar},
3 title = {GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo},
4 year = {2023},
5 publisher = {GitHub},
6 journal = {GitHub repository},
7 howpublished = {\url{https://github.com/nomic-ai/gpt4all}},
8}
bibtex
1@misc{alpaca,
2 author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
3 title = {Stanford Alpaca: An Instruction-following LLaMA model},
4 year = {2023},
5 publisher = {GitHub},
6 journal = {GitHub repository},
7 howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
8}
bibtex
1@software{leandro_von_werra_2023_7790115,
2 author = {Leandro von Werra and
3 Alex Havrilla and
4 Max reciprocated and
5 Jonathan Tow and
6 Aman cat-state and
7 Duy V. Phung and
8 Louis Castricato and
9 Shahbuland Matiana and
10 Alan and
11 Ayush Thakur and
12 Alexey Bukhtiyarov and
13 aaronrmm and
14 Fabrizio Milo and
15 Daniel and
16 Daniel King and
17 Dong Shin and
18 Ethan Kim and
19 Justin Wei and
20 Manuel Romero and
21 Nicky Pochinkov and
22 Omar Sanseviero and
23 Reshinth Adithyan and
24 Sherman Siu and
25 Thomas Simonini and
26 Vladimir Blagojevic and
27 Xu Song and
28 Zack Witten and
29 alexandremuzio and
30 crumb},
31 title = {{CarperAI/trlx: v0.6.0: LLaMa (Alpaca), Benchmark
32 Util, T5 ILQL, Tests}},
33 month = mar,
34 year = 2023,
35 publisher = {Zenodo},
36 version = {v0.6.0},
37 doi = {10.5281/zenodo.7790115},
38 url = {https://doi.org/10.5281/zenodo.7790115}
39}
