Hugging Face's logo

TheBloke
/
airoboros-13b-gpt4-1.4-SuperHOT-8K-GPTQ

Text Generation
Transformers
Safetensors
llama
custom_code
text-generation-inference
4-bit precision
gptq
Model card Files Community
1
Edit model card
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

Jon Durbin's Airoboros 13B GPT4 1.4 GPTQ

These files are GPTQ 4bit model files for Jon Durbin's Airoboros 13B GPT4 1.4 merged with Kaio Ken's SuperHOT 8K.

It is the result of quantising to 4bit using GPTQ-for-LLaMa.

This is an experimental new GPTQ which offers up to 8K context size

The increased context is tested to work with ExLlama, via the latest release of text-generation-webui.

It has also been tested from Python code using AutoGPTQ, and trust_remote_code=True.

Code credits:

  • Original concept and code for increasing context length: kaiokendev
  • Updated Llama modelling code that includes this automatically via trust_remote_code: emozilla.

Please read carefully below to see how to use it.

GGML versions are not yet provided, as there is not yet support for SuperHOT in llama.cpp. This is being investigated and will hopefully come soon.

Repositories available

Prompt template 

A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input
USER: prompt
ASSISTANT:

How to easily download and use this model in text-generation-webui with ExLlama

Please make sure you're using the latest version of text-generation-webui

  1. Click the Model tab.
  2. Under Download custom model or LoRA, enter TheBloke/airoboros-13b-gpt4-1.4-SuperHOT-8K-GPTQ.
  3. Click Download.
  4. The model will start downloading. Once it's finished it will say "Done"
  5. Untick Autoload the model
  6. In the top left, click the refresh icon next to Model.
  7. In the Model dropdown, choose the model you just downloaded: airoboros-13b-gpt4-1.4-SuperHOT-8K-GPTQ
  8. To use the increased context, set the Loader to ExLlama, set max_seq_len to 8192 or 4096, and set compress_pos_emb to 4 for 8192 context, or to 2 for 4096 context.
  9. Now click Save Settings followed by Reload
  10. The model will automatically load, and is now ready for use!
  11. Once you're ready, click the Text Generation tab and enter a prompt to get started!

How to use this GPTQ model from Python code with AutoGPTQ

First make sure you have AutoGPTQ and Einops installed:

pip3 install einops auto-gptq

Then run the following code. Note that in order to get this to work, config.json has been hardcoded to a sequence length of 8192.

If you want to try 4096 instead to reduce VRAM usage, please manually edit config.json to set max_position_embeddings to the value you want.

from transformers import AutoTokenizer, pipeline, logging
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import argparse

model_name_or_path = "TheBloke/airoboros-13b-gpt4-1.4-SuperHOT-8K-GPTQ"
model_basename = "airoboros-13b-gpt4-1.4-superhot-8k-GPTQ-4bit-128g.no-act.order"

use_triton = False

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)

model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
        model_basename=model_basename,
        use_safetensors=True,
        trust_remote_code=True,
        device_map='auto',
        use_triton=use_triton,
        quantize_config=None)

model.seqlen = 8192

# Note: check the prompt template is correct for this model.
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''

print("\n\n*** Generate:")

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))

# Inference can also be done using transformers' pipeline

# Prevent printing spurious transformers error when using pipeline with AutoGPTQ
logging.set_verbosity(logging.CRITICAL)

print("*** Pipeline:")
pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.15
)

print(pipe(prompt_template)[0]['generated_text'])

Using other UIs: monkey patch

Provided in the repo is llama_rope_scaled_monkey_patch.py, written by @kaiokendev.

It can be theoretically be added to any Python UI or custom code to enable the same result as trust_remote_code=True. I have not tested this, and it should be superseded by using trust_remote_code=True, but I include it for completeness and for interest.

Provided files

airoboros-13b-gpt4-1.4-superhot-8k-GPTQ-4bit-128g.no-act.order.safetensors

This will work with AutoGPTQ, ExLlama, and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.

It was created with group_size 128 to increase inference accuracy, but without --act-order (desc_act) to increase compatibility and improve inference speed.

  • airoboros-13b-gpt4-1.4-superhot-8k-GPTQ-4bit-128g.no-act.order.safetensors
    • Works for use with ExLlama with increased context (4096 or 8192)
    • Works with AutoGPTQ in Python code, including with increased context, if trust_remote_code=True is set.
    • Should work with GPTQ-for-LLaMa in CUDA mode, but unknown if increased context works - TBC. May have issues with GPTQ-for-LLaMa Triton mode.
    • Works with text-generation-webui, including one-click-installers.
    • Parameters: Groupsize = 128. Act Order / desc_act = False.

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: Aemon Algiz.

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, 闃挎槑, 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 Wikie艂, 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 model card: Kaio Ken's SuperHOT 8K

SuperHOT Prototype 2 w/ 8K Context

This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in the github blog. Tests have shown that the model does indeed leverage the extended context at 8K.

You will need to use either the monkeypatch or, if you are already using the monkeypatch, change the scaling factor to 0.25 and the maximum sequence length to 8192

Looking for Merged & Quantized Models?

Training Details

I trained the LoRA with the following configuration:

  • 1200 samples (~400 samples over 2048 sequence length)
  • learning rate of 3e-4
  • 3 epochs
  • The exported modules are:
    • q_proj
    • k_proj
    • v_proj
    • o_proj
    • no bias
  • Rank = 4
  • Alpha = 8
  • no dropout
  • weight decay of 0.1
  • AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
  • Trained on 4-bit base model

Original model card: Jon Durbin's Airoboros 13B GPT4 1.4

update 2023-06-25 - re-uploaded with a slightly earlier checkpoint, which seems perhaps a little less overfit than the full 3-epochs version initially uploaded

Overview

This is a full (not qlora) fine-tune 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros

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

  • fixed (+ more examples of) multi-character, multi-turn conversations
  • coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
  • 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 FastChat

The prompt it was trained with was:

A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. 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-13b-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 single space 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.

Downloads last month
33
Safetensors
Model size
2.03B params
Tensor type
F32
路
I32
路
FP16
路
Inference Examples
Text Generation
Inference API (serverless) has been turned off for this model.