<!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end -->

OpenAccess AI Collective's Manticore 13B Chat fp16

This is fp16 pytorch format model files for OpenAccess AI Collective's Manticore 13B Chat merged with Kaio Ken's SuperHOT 8K.

Kaio Ken's SuperHOT 13b LoRA is merged on to the base model, and then 8K context can be achieved during inference by using trust_remote_code=True.

Note that config.json has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.

Repositories available

How to use this model from Python code

First make sure you have Einops installed:

pip3 install auto-gptq

Then run the following code. config.json has been default to a sequence length of 8192, but you can also configure this in your Python code.

The provided modelling code, activated with trust_remote_code=True will automatically set the scale parameter from the configured max_position_embeddings. Eg for 8192, scale is set to 4.

from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse

model_name_or_path = "TheBloke/Manticore-13B-Chat-Pyg-SuperHOT-8K-fp16"

use_triton = False

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

config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192

model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
        config=config,
        trust_remote_code=True,
        device_map='auto')

# Note: check to confirm if this is correct 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

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.

<!-- footer start -->

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!

<!-- footer end -->

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:

Original model card: OpenAccess AI Collective's Manticore 13B Chat

Manticore 13B Chat

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

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.

Manticore 13B

Not added from Manticore 13B:

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.

Release Notes

Build

Manticore was built with Axolotl on 8xA100 80GB

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.

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.