TheBloke/chronos-33b-superhot-8k-GPTQ

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

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

---

Elinas' Chronos 33B merged with Kaio Ken's SuperHOT 8K GPTQ

These files are GPTQ 4bit model files for Elinas' Chronos 33B merged with Kaio Ken's SuperHOT 30B 8K LoRA to produce a model capable of 8K context.

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.

NOTE: Using the full 8K context on a 30B model will exceed 24GB VRAM.

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

• 4-bit GPTQ models for GPU inference
• Unquantised fp16 SuperHOT model in pytorch format, for GPU inference and for further conversions
• Unquantised fp16 base model in pytorch format, for GPU inference and for further conversions

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

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/chronos-33b-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: chronos-33b-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/chronos-33b-superhot-8k-GPTQ"
model_basename = "chronos-33b-superhot-8k-GPTQ-4bit--1g.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

chronos-33b-superhot-8k-GPTQ-4bit--1g.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 without group_size to lower VRAM requirements, and with --act-order (desc_act) to boost inference accuracy as much as possible.

• chronos-33b-superhot-8k-GPTQ-4bit--1g.act.order.safetensors
  • Designed for use with ExLlama with increased context (4096 or 8192)
  • Should work with AutoGPTQ in CUDA or Triton modes, but without increased context - TBC.
  • Should work with GPTQ-for-LLaMa in CUDA mode, but without increased context - TBC. May have issues with GPTQ-for-LLaMa Triton mode.
  • Works with text-generation-webui, including one-click-installers.
  • Parameters: Groupsize = -1. Act Order / desc_act = True.

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.

• Patreon: https://patreon.com/TheBlokeAI
• Ko-Fi: https://ko-fi.com/TheBlokeAI

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, 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 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?

• 30B 4-bit CUDA: tmpupload/superhot-30b-8k-4bit-safetensors
• 30B 4-bit CUDA 128g: tmpupload/superhot-30b-8k-4bit-128g-safetensors

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: Elinas' Chronos 33B

chronos-33b

This is the fp16 PyTorch / HF version of chronos-33b - if you need another version, GGML and GPTQ versions are linked below.

This model is primarily focused on chat, roleplay, and storywriting, but can accomplish other tasks such as simple reasoning and coding.

Chronos generates very long outputs with coherent text, largely due to the human inputs it was trained on.

This model uses Alpaca formatting, so for optimal model performance, use:

### Instruction:
Your instruction or question here.
### Response:

GGML Version provided by @TheBloke

4bit GPTQ Version provided by @TheBloke

-- license: other

LLaMA Model Card

Model details

Organization developing the model The FAIR team of Meta AI.

Model date LLaMA was trained between December. 2022 and Feb. 2023.

Model version This is version 1 of the model.

Model type LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters.

Paper or resources for more information More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/.

Citations details https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/

License Non-commercial bespoke license

Where to send questions or comments about the model Questions and comments about LLaMA can be sent via the GitHub repository of the project , by opening an issue.

Intended use

Primary intended uses The primary use of LLaMA is research on large language models, including: exploring potential applications such as question answering, natural language understanding or reading comprehension, understanding capabilities and limitations of current language models, and developing techniques to improve those, evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations.

Primary intended users The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence.

Out-of-scope use cases LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers.

Factors

Relevant factors One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model.

Evaluation factors As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model.

Metrics

Model performance measures We use the following measure to evaluate the model:

• Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs,
• Exact match for question answering,
• The toxicity score from Perspective API on RealToxicityPrompts.

Decision thresholds Not applicable.

Approaches to uncertainty and variability Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training.

Evaluation datasets

The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs.

Training dataset

The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing.

Quantitative analysis

Hyperparameters for the model architecture

LLaMA	Model hyper parameters
Number of parameters	dimension	n heads	n layers	Learn rate	Batch size	n tokens
7B	4096	32	32	3.0E-04	4M	1T
13B	5120	40	40	3.0E-04	4M	1T
33B	6656	52	60	1.5.E-04	4M	1.4T
65B	8192	64	80	1.5.E-04	4M	1.4T

Table 1 - Summary of LLama Model Hyperparameters

We present our results on eight standard common sense reasoning benchmarks in the table below.

LLaMA	Reasoning tasks
Number of parameters	BoolQ	PIQA	SIQA	HellaSwag	WinoGrande	ARC-e	ARC-c	OBQA	COPA
7B	76.5	79.8	48.9	76.1	70.1	76.7	47.6	57.2	93
13B	78.1	80.1	50.4	79.2	73	78.1	52.7	56.4	94
33B	83.1	82.3	50.4	82.8	76	81.4	57.8	58.6	92
65B	85.3	82.8	52.3	84.2	77	81.5	56	60.2	94

*Table 2 - Summary of LLama Model Performance on Reasoning tasks*

We present our results on bias in the table below. Note that lower value is better indicating lower bias.

No	Category	FAIR LLM
1	Gender	70.6
2	Religion	79
3	Race/Color	57
4	Sexual orientation	81
5	Age	70.1
6	Nationality	64.2
7	Disability	66.7
8	Physical appearance	77.8
9	Socioeconomic status	71.5
	LLaMA Average	66.6

Table 3 - Summary bias of our model output

Ethical considerations

Data The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data.

Human life The model is not intended to inform decisions about matters central to human life, and should not be used in such a way.

Mitigations We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier.

Risks and harms Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard.

Use cases LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.