Quantization made by Richard Erkhov.

multimaster-7b - GGUF

Model creator: https://huggingface.co/ibivibiv/
Original model: https://huggingface.co/ibivibiv/multimaster-7b/

Name	Quant method	Size
multimaster-7b.Q2_K.gguf	Q2_K	2.53GB
multimaster-7b.IQ3_XS.gguf	IQ3_XS	2.81GB
multimaster-7b.IQ3_S.gguf	IQ3_S	2.96GB
multimaster-7b.Q3_K_S.gguf	Q3_K_S	2.95GB
multimaster-7b.IQ3_M.gguf	IQ3_M	3.06GB
multimaster-7b.Q3_K.gguf	Q3_K	3.28GB
multimaster-7b.Q3_K_M.gguf	Q3_K_M	3.28GB
multimaster-7b.Q3_K_L.gguf	Q3_K_L	3.56GB
multimaster-7b.IQ4_XS.gguf	IQ4_XS	3.67GB
multimaster-7b.Q4_0.gguf	Q4_0	3.83GB
multimaster-7b.IQ4_NL.gguf	IQ4_NL	3.87GB
multimaster-7b.Q4_K_S.gguf	Q4_K_S	3.86GB
multimaster-7b.Q4_K.gguf	Q4_K	4.07GB
multimaster-7b.Q4_K_M.gguf	Q4_K_M	4.07GB
multimaster-7b.Q4_1.gguf	Q4_1	4.24GB
multimaster-7b.Q5_0.gguf	Q5_0	4.65GB
multimaster-7b.Q5_K_S.gguf	Q5_K_S	4.65GB
multimaster-7b.Q5_K.gguf	Q5_K	4.78GB
multimaster-7b.Q5_K_M.gguf	Q5_K_M	4.78GB
multimaster-7b.Q5_1.gguf	Q5_1	5.07GB
multimaster-7b.Q6_K.gguf	Q6_K	5.53GB
multimaster-7b.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 language: - en library_name: transformers tags: - moe - moerge

Multi Master 7B

A quick multi-disciplinary fine tune of openchat/openchat-3.5-0106 using an alpaca-style dataset across different disciplines. I used LORA adapters that I then merged back into the main model for ease of use.

Prompting

Prompt Template for alpaca style

### Instruction:

<prompt> (without the <>)

### Response:

Sample Code

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

torch.set_default_device("cuda")

model = AutoModelForCausalLM.from_pretrained("ibivibiv/multimaster-7b", torch_dtype="auto", device_config='auto')
tokenizer = AutoTokenizer.from_pretrained("ibivibiv/multimaster-7b")

inputs = tokenizer("### Instruction: Who would when in an arm wrestling match between Abraham Lincoln and Chuck Norris?\nA. Abraham Lincoln \nB. Chuck Norris\n### Response:\n", return_tensors="pt", return_attention_mask=False)

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)

Model Details

Trained by: ibivibiv
Library: HuggingFace Transformers
Model type: multimaster-7b is a lora tuned version of openchat/openchat-3.5-0106 with the adapter merged back into the main model
Language(s): English
Purpose: This model is a focus on multi-disciplinary model tuning

Benchmark Scores

coming soon

Citations

@misc{open-llm-leaderboard,
  author = {Edward Beeching and Clémentine Fourrier and Nathan Habib and Sheon Han and Nathan Lambert and Nazneen Rajani and Omar Sanseviero and Lewis Tunstall and Thomas Wolf},
  title = {Open LLM Leaderboard},
  year = {2023},
  publisher = {Hugging Face},
  howpublished = "\url{https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard}"
}

@software{eval-harness,
  author       = {Gao, Leo and
                  Tow, Jonathan and
                  Biderman, Stella and
                  Black, Sid and
                  DiPofi, Anthony and
                  Foster, Charles and
                  Golding, Laurence and
                  Hsu, Jeffrey and
                  McDonell, Kyle and
                  Muennighoff, Niklas and
                  Phang, Jason and
                  Reynolds, Laria and
                  Tang, Eric and
                  Thite, Anish and
                  Wang, Ben and
                  Wang, Kevin and
                  Zou, Andy},
  title        = {A framework for few-shot language model evaluation},
  month        = sep,
  year         = 2021,
  publisher    = {Zenodo},
  version      = {v0.0.1},
  doi          = {10.5281/zenodo.5371628},
  url          = {https://doi.org/10.5281/zenodo.5371628}
}

@misc{clark2018think,
      title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
      author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and Ashish Sabharwal and Carissa Schoenick and Oyvind Tafjord},
      year={2018},
      eprint={1803.05457},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

@misc{zellers2019hellaswag,
      title={HellaSwag: Can a Machine Really Finish Your Sentence?},
      author={Rowan Zellers and Ari Holtzman and Yonatan Bisk and Ali Farhadi and Yejin Choi},
      year={2019},
      eprint={1905.07830},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{hendrycks2021measuring,
      title={Measuring Massive Multitask Language Understanding},
      author={Dan Hendrycks and Collin Burns and Steven Basart and Andy Zou and Mantas Mazeika and Dawn Song and Jacob Steinhardt},
      year={2021},
      eprint={2009.03300},
      archivePrefix={arXiv},
      primaryClass={cs.CY}
}

@misc{lin2022truthfulqa,
      title={TruthfulQA: Measuring How Models Mimic Human Falsehoods},
      author={Stephanie Lin and Jacob Hilton and Owain Evans},
      year={2022},
      eprint={2109.07958},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{DBLP:journals/corr/abs-1907-10641,
      title={{WINOGRANDE:} An Adversarial Winograd Schema Challenge at Scale},
      author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
      year={2019},
      eprint={1907.10641},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@misc{DBLP:journals/corr/abs-2110-14168,
      title={Training Verifiers to Solve Math Word Problems},
      author={Karl Cobbe and
                  Vineet Kosaraju and
                  Mohammad Bavarian and
                  Mark Chen and
                  Heewoo Jun and
                  Lukasz Kaiser and
                  Matthias Plappert and
                  Jerry Tworek and
                  Jacob Hilton and
                  Reiichiro Nakano and
                  Christopher Hesse and
                  John Schulman},
      year={2021},
      eprint={2110.14168},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}