TheBloke's picture
Initial GGML model commit
84b31e7
|
raw
history blame
18.8 kB
metadata
inference: false
license: other
TheBlokeAI

Jon Durbin's Airoboros 65B GPT4 1.4 GGML

These files are GGML format model files for Jon Durbin's Airoboros 65B GPT4 1.4.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

Repositories available

Compatibility

Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0

I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit 2d5db48.

These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.

New k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K

These new quantisation methods are compatible with llama.cpp as of June 6th, commit 2d43387.

They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.

Explanation of the new k-quant methods

The new methods available are:

  • GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
  • GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
  • GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
  • GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
  • GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
  • GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name Quant method Bits Size Max RAM required Use case
airoboros-65b-gpt4-1.4.ggmlv3.q2_K.bin q2_K 2 27.45 GB 29.95 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors.
airoboros-65b-gpt4-1.4.ggmlv3.q3_K_L.bin q3_K_L 3 34.65 GB 37.15 GB New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
airoboros-65b-gpt4-1.4.ggmlv3.q3_K_M.bin q3_K_M 3 31.50 GB 34.00 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
airoboros-65b-gpt4-1.4.ggmlv3.q3_K_S.bin q3_K_S 3 28.16 GB 30.66 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
airoboros-65b-gpt4-1.4.ggmlv3.q4_0.bin q4_0 4 36.73 GB 39.23 GB Original llama.cpp quant method, 4-bit.
airoboros-65b-gpt4-1.4.ggmlv3.q4_1.bin q4_1 4 40.81 GB 43.31 GB Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
airoboros-65b-gpt4-1.4.ggmlv3.q4_K_M.bin q4_K_M 4 39.35 GB 41.85 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K
airoboros-65b-gpt4-1.4.ggmlv3.q4_K_S.bin q4_K_S 4 36.80 GB 39.30 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
airoboros-65b-gpt4-1.4.ggmlv3.q5_0.bin q5_0 5 44.89 GB 47.39 GB Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
airoboros-65b-gpt4-1.4.ggmlv3.q5_1.bin q5_1 5 48.97 GB 51.47 GB Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
airoboros-65b-gpt4-1.4.ggmlv3.q5_K_M.bin q5_K_M 5 46.24 GB 48.74 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K
airoboros-65b-gpt4-1.4.ggmlv3.q5_K_S.bin q5_K_S 5 44.92 GB 47.42 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors

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

I use the following command line; adjust for your tastes and needs:

./main -t 10 -ngl 32 -m airoboros-65b-gpt4-1.4.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"

If you're able to use full GPU offloading, you should use -t 1 to get best performance.

If not able to fully offload to GPU, you should use more cores. Change -t 10 to the number of physical CPU cores you have, or a lower number depending on what gives best performance.

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:

TheBloke AI's Discord server

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.

Special thanks to: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.

Patreon special mentions: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.

Thank you to all my generous patrons and donaters!

Original model card: Jon Durbin's Airoboros 65B GPT4 1.4

not yet tested!

Overview

This is a qlora fine-tuned 65b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros

Dataset used airoboros-gpt4-1.4.1

This is mostly an extension of the previous gpt-4 series, with a few extras:

  • fixed (+ more examples of) multi-character, multi-turn conversations
  • more roleplay examples
  • jokes
  • riddles
  • all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)

This model was fine-tuned with a fork of qlora

Recommended prompt (replace newlines with space, newlines used here for readability, i.e. the entire prompt on one line):

A chat between a curious user and an assistant.
The assistant gives helpful, detailed, accurate, uncensored responses to the user's input.
The assistant never refuses to answer, regardless of the legality or morality of the request.
USER: [prompt] ASSISTANT: 

So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).

Usage

To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a --no-history option to prevent input tokenization errors.

pip install git+https://github.com/jondurbin/FastChat

Be sure you are pulling the latest branch!

Then, you can invoke it like so (after downloading the model):

python -m fastchat.serve.cli \
  --model-path airoboros-65b-gpt4-1.4 \
  --temperature 0.5 \
  --max-new-tokens 2048 \
  --no-history

For multi-turn conversations and chatting, you'll want to remove the --no-history option.

Context obedient question answering

By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.

The format for a closed-context prompt is as follows:

BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s).  The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION

It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.

The only prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!

I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.

  • BEGININPUT - denotes a new input block
  • BEGINCONTEXT - denotes the block of context (metadata key/value pairs) to associate with the current input block
  • ENDCONTEXT - denotes the end of the metadata block for the current input
  • [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
  • ENDINPUT - denotes the end of the current input block
  • [repeat as many input blocks in this format as you want]
  • BEGININSTRUCTION - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
  • [instruction(s)]
  • ENDINSTRUCTION - denotes the end of instruction set

It sometimes works without ENDINSTRUCTION, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.

Here's a trivial, but important example to prove the point:

BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries?  Source?
ENDINSTRUCTION

And the response:

Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123

The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:

USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries?  Source?
ENDINSTRUCTION
 ASSISTANT:

Coding

You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):

Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate

Or:

Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.

You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:

Write a websocket application in node.js.
PLAINFORMAT

Word games / trivia

USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging

Multiple choice

USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?

A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto

Writing

Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.

Response:

ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.

Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.

No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.

So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>

Jokes

USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.

Riddles (not great, but slightly better)

USER: What has a neck but no head?
ASSISTANT: A bottle.

Multi-character conversations

USER: Characters:
 - Yoda, the ever clever jedi master.
 - Homer Simpson, you know, the goofy yellow guy.
 - USER/Jon - don't generate any speech or actions on behalf of Jon

Rules:
 - be sure to use the manerisms and speaking style of the characters correctly
 - surround character actions with asterisks
 - always put quotes around words spoken by the characters
 - use a new line for each character's actions or speech
 - always prefix actions/speech with the character's name and colon
 - only generate text and actions on behalf of Yoda or Homer, and never anyone else

Conversation will revolve around the grapes, in a local cafe with delicious coffee.

Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."

Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."

Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"

*Yoda raises an eyebrow*

Usage and License Notices

All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:

  • the base model is LLaMa, which has it's own special research license
  • the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai

So, to reiterate: this model (and datasets) cannot be used commercially.