Chat & support: my new Discord server

Want to contribute? TheBloke's Patreon page

OpenAccess AI Collective's Manticore 13B Chat GPTQ

These files are GPTQ 4bit model files for OpenAccess AI Collective's Manticore 13B Chat 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

• 4-bit GPTQ models for GPU inference
• 2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference
• Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions
• Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions

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

Click the Model tab .

Under Download custom model or LoRA , enter TheBloke/Manticore-13B-Chat-Pyg-SuperHOT-8K-GPTQ .

Click Download .

The model will start downloading. Once it's finished it will say "Done"

Untick Autoload the model

In the top left, click the refresh icon next to Model .

In the Model dropdown, choose the model you just downloaded: Manticore-13B-Chat-Pyg-SuperHOT-8K-GPTQ

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.

Now click Save Settings followed by Reload

The model will automatically load, and is now ready for use!

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/Manticore-13B-Chat-Pyg-SuperHOT-8K-GPTQ"
model_basename = "manticore-13b-chat-pyg-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

manticore-13b-chat-pyg-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.

• manticore-13b-chat-pyg-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.

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

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: 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: OpenAccess AI Collective's Manticore 13B Chat

Manticore 13B Chat

Manticore 13B Chat builds on Manticore with new datasets, including 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

Manticore 13B Chat is a Llama 13B model fine-tuned on the following datasets along with the datasets from the original Manticore 13B.

Manticore 13B Chat was trained on 25% of the datasets below. The datasets were merged, shuffled, and then sharded into 4 parts.

• de-duped pygmalion dataset, filtered down to RP data
• riddle_sense - instruct augmented
• hellaswag, updated for detailed explanations w 30K+ rows
• gsm8k - instruct augmented
• ewof/code-alpaca-instruct-unfiltered

Manticore 13B

• ShareGPT - based on a cleaned and de-suped subset
• WizardLM
• Wizard-Vicuna
• subset of QingyiSi/Alpaca-CoT for roleplay and CoT
• GPT4-LLM-Cleaned
• GPTeacher-General-Instruct
• ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the train split
• hellaswag - 5K row subset of instruct augmented for concise responses, derived from the train split
• metaeval/ScienceQA_text_only - instruct for concise responses
• openai/summarize_from_feedback - instruct augmented tl;dr summarization

Not added from Manticore 13B:

• mmlu - mmlu datasets were not added to this model as the test split is used for benchmarks

Shoutouts

Special thanks to Nanobit for helping with Axolotl, TheBloke for quantizing these models are more accessible to all, ehartford for cleaned datasets, and 0x000011b for the RP dataset.

Demo

Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.

• https://huggingface.co/spaces/openaccess-ai-collective/manticore-13b-chat-pyg

Release Notes

• https://wandb.ai/wing-lian/manticore-13b-v2/runs/hxr3aiiw

Build

Manticore was built with Axolotl on 8xA100 80GB

• 3 epochs taking approximately 8 hours. No further epochs will be released.
• The configuration to duplicate this build is provided in this repo's /config folder .

Bias, Risks, and Limitations

Manticore 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). Manticore was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.

Examples

USER: make up a sonnet in the style of shakespeare about a skier skiing in the glades on a bluebird day.
ASSISTANT: A skier doth glide 'neath sun’s glow, His edges sharp to cut the snow, Bluebird sky above, While he doth revel on the slopes below, The cold air biting his nose, But not his spirits, For he is filled with a sense of joy, As he carves through the powdery drifts. His body moves in graceful rhythm, And each turn he makes with ease, He feels like he could ski forever, With no care for the world outside these glades.

USER: tell me a joke about alpacas
ASSISTANT: Did you hear about the famous alpaca ballet dancer? She was a prima llama.
USER: okay, that is actually pretty good
ASSISTANT: What do you call an alpaca in a bowtie? A llama-cholla!
USER: why is that funny?
ASSISTANT: Because it’s a play on words. “Llama-cholla” sounds like “lame chola,” which is Spanish slang for someone who acts cool or pretentious. So, the joke is implying that alpacas are vain and act cool with their bowties.

USER: What is 44 + 77?
ASSISTANT: 121
USER: What is the sum of 33 and 77?
ASSISTANT: 110
USER: tell me 5 words that start with “ex” and the sum of 33 and 77.
ASSISTANT: exotic, expressive, explicit, experimental, and extravagant. The sum of 33 and 77 is 110.
USER: tell me 3 words that start with “egr” and end in “s”
ASSISTANT: egret, eggplant, and egrets.

• oof

USER: Sally has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?
ASSISTANT: Sally has a total of 6 siblings, so she has a total of 6 - 2 = 4 sisters.
USER: Sally has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have? Use multi-step reasoning to explain your answer.
ASSISTANT: Sally has a total of three brothers, so she has a total of three * 2 = six siblings. Her family consists of three boys and six girls in total. This means that Sally has three sisters since there are six female relatives and only three male ones.
USER: But when brothers have sisters, aren’t they shared or the same?
ASSISTANT: No, not every sibling shares their mother. For example, I have two brothers who share one mother but my third brother has a different mother from both of them.
USER: Let’s assume they all share the same mother and father. Now explain with multi-step reasoning.
ASSISTANT: If Sally has three brothers then that means she has six siblings altogether. Each brother has two sisters, which means that there are twelve female relatives in her family - one for each of her brothers and herself. Since there are only six females in the entire family, that means that Sally’s mother has no other children than her own three sons - so she can’t be the mother of any of the sisters. So all those sisters have to belong to one of the brothers, and since they are shared by two brothers, then each brother has a single sister. Therefore, there is only one sister for Sally, making the final answer 1.

• pretty sure that reasoning isn't correct, and the final answer of having 1 sister is a lucky guess