inference: false
license: other
datasets:
- QingyiSi/Alpaca-CoT
- teknium/GPT4-LLM-Cleaned
- teknium/GPTeacher-General-Instruct
- metaeval/ScienceQA_text_only
- hellaswag
- openai/summarize_from_feedback
- riddle_sense
- gsm8k
- OpenAssistant/oasst1
language:
- en
library_name: transformers
pipeline_tag: text-generation
OpenAccess AI Collective's Hippogriff 30B Chat GGML
These files are GGML format model files for OpenAccess AI Collective's Hippogriff 30B Chat.
GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:
Repositories available
- 4-bit GPTQ models for GPU inference
- 4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference
- Unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template
You are a helpful assistant
USER: prompt goes here
ASSISTANT:
or
<|system|> You are a helpful assistant
<|user|> prompt goes here
<|model|>
THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit 2d5db48 or later) to use them.
Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|---|---|---|---|---|---|
| hippogriff-30b.ggmlv3.q4_0.bin | q4_0 | 4 | 18.30 GB | 20.80 GB | 4-bit. |
| hippogriff-30b.ggmlv3.q4_1.bin | q4_1 | 4 | 20.33 GB | 22.83 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| hippogriff-30b.ggmlv3.q5_0.bin | q5_0 | 5 | 22.37 GB | 24.87 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
| hippogriff-30b.ggmlv3.q5_1.bin | q5_1 | 5 | 24.40 GB | 26.90 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
| hippogriff-30b.ggmlv3.q8_0.bin | q8_0 | 8 | 34.56 GB | 37.06 GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
How to run in llama.cpp
Here is an example command line. Adjust for your tastes and needs:
./main -t 10 -ngl 32 -m hippogriff-30b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|system|> You are a story writing assistant\n<|user|> prompt\n<|model|>"
Change -t 10 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.
Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins
How to run in text-generation-webui
Further instructions here: text-generation-webui/docs/llama.cpp-models.md.
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute.
Thanks to the chirper.ai team!
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
Patreon special mentions: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
Original model card: OpenAccess AI Collective's Hippogriff 30B Chat
Hippogriff 30B Chat
Hippogriff 30B Chat is an experiment that builds on Manticore with new datasets, while removing a few more instruction and chat datasets. It also includes a de-duped subset of the Pygmalion dataset. It also removes all Alpaca style prompts using ### in favor of
chat only style prompts using USER:,ASSISTANT: as well as pygmalion/metharme prompting using <|system|>, <|user|> and <|model|> tokens.
Questions, comments, feedback, looking to donate, or want to help? Reach out on our Discord or email wing@openaccessaicollective.org
Training Datasets
Hippogriff 30B Chat is a Llama 30B model fine-tuned on the following datasets
- OpenAssistant/oasst1 - cleaned dataset, similar to Guanaco
- synthetic jokes generation and explanation derived from reddit jokes dataset
- synthetic prose generation and rewriting self-chat
- Q&A based on provided context
- self instruct augmented logic_inference_oa
- de-duped pygmalion dataset, filtered down to RP data, cleaned, english only, 25%
- riddle_sense - instruct augmented
- hellaswag, updated for detailed explanations w 30K+ rows
- gsm8k - instruct augmented
- ewof/code-alpaca-instruct-unfiltered synthetic self chat dataset derived from about 1000 rows
- subset of QingyiSi/Alpaca-CoT for roleplay and CoT
- GPTeacher-General-Instruct
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the
trainsplit - hellaswag - 5K row subset of instruct augmented for concise responses, derived from the
trainsplit - metaeval/ScienceQA_text_only - instruct for concise responses
- openai/summarize_from_feedback - instruct augmented tl;dr summarization
Hippogriff differs from Manticore as it does not use the WizardLM, WizardVicuna, Alpaca, or ShareGPT datasets.
Initial thoughts
Hippogriff follows instructions pretty well. It still struggles with anything that has to do with math. Prose is much better than manticore. Handles in-context QA much better.
Shoutouts
Special thanks to Nanobit for helping with Axolotl, TheBloke for quantizing these models are more accessible to all, 0x000011b for the RP dataset, and the support from everyone in our AI Discord community.
Demo
A Spaces demo is not provided for this release due to 30B models currently not fitting in VRAM.
Build
Hippogriff was built with Axolotl on 8xA100 80GB
- 1.5 epochs taking approximately 12 hours. No further epochs will be released.
Bias, Risks, and Limitations
Hippogriff has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). Hippogriff was fine-tuned from the base model LlaMa 30B, please refer to its model card's Limitations Section for relevant information.
The core functionality of Llama is taking a string of text and predicting the next token. While language models are widely used for tasks other than this, there are a lot of unknowns with this work. When prompting Hippogriff it is important to remember that the statistically most likely next token is often not the token that produces the most "accurate" text. Never depend upon Hippogriff to produce factually accurate output.
Llama was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending upon use case Hippogriff may produce socially unacceptable text. See Sections 5 and 6 of the Pile paper for a more detailed analysis of the biases in the Pile.
As with all language models, it is hard to predict in advance how Hippogriff will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.
Examples
TBD
USER: write an original short story of at least 300 words in the style of Zora Neale Hurston. Incorporate the following literary devices: Euphemism and Foreshadowing.
ASSISTANT: Once upon a time, there was a black girl named Rose, whose skin shined like a pearl beneath the hot sun. She lived with her mama and daddy on their farm, where they grew crops to feed the family and neighbors. On this particular day, Rose felt a tinge of excitement as she watched her parents work diligently in their fields. 'It's almost harvest season!' she thought, imagining the delicious meals that awaited them. But, soon after, it became apparent that something sinister lurked amidst the rows of fresh produce.
As her father hoed around a vine-covered cucumber plant, he unearthed a peculiar rock. It was the size of an acorn but had a strange shape, unlike anything he or his wife had ever seen. "What have we here?" He said, turning to his wife with curiosity and excitement. She examined the rock for herself and declared, "Why, it looks like a piece of coal!" But as both mother and daughter looked closer, it seemed to be far more than a mere piece of coal. A sense of unease crept up Rose's spine when she noticed that the rock resembled the dark face of a baby in the womb. As Rose tried to suppress a scream, her mother gasped, "Sweet Jesus! Let's bury this thing before anyone sees!" And so, they quickly hid the stone back underground, hoping that nobody would ever discover their secret.
USER: tell me 5 words that start with "ex" and then the sum of 33 and 77
ASSISTANT: Excite, exotic, exhibit, excitable, excessive
USER: sally (a girl) has 3 brothers. Each brother has 2 sisters. how many sisters does sally have?
ASSISTANT: Sally has 3 brothers, and each brother has 2 sisters. To find out how many sisters Sally has in total, we need to multiply the number of bro
thers by the number of sisters per brother, then add 1 to account for Sally herself. So, 3 * 2 + 1 = 6 sisters in total