Locutusque's picture
Update README.md
e6ea13e verified
metadata
library_name: transformers
tags:
  - code
  - chemistry
  - medical
license: apache-2.0
datasets:
  - Locutusque/hyperion-v3.0
language:
  - en
widget:
  - example_title: Reasoning
    text: >
      <|im_start|>user

      An astronomer observes that a planet rotates faster after a meteorite
      impact. Which is the most likely effect of this increase in rotation? A.
      Planetary density will decrease. B. Planetary years will become longer. C.
      Planetary days will become shorter. D. Planetary gravity will become
      stronger.<|im_end|>

      <|im_start|>assistant
    output:
      text: >
        C. Planetary days will become shorter.


        The increase in rotation is due to the transfer of angular momentum from
        the meteorite impact to the planet. This means that more kinetic energy
        is imparted on the planet, making it spin faster. As a result, the
        planet's rotational period (the time it takes for the planet to complete
        one rotation) decreases. So, planetary days will become shorter.


        A. Planetary density will not change significantly as a result of the
        meteorite impact. The increase in rotation is primarily an issue of
        angular momentum transfer, and density is mainly determined by the
        composition of the planet. 


        B. Planetary years would become longer if the planet took less time to
        rotate around its axis, since a year is based on how long it takes the
        planet to revolve around its star. However, meteorite impacts generally
        affect rotation, not revolution.


        D. Planetary gravity would remain the same or possibly slightly
        decrease. A meteorite impact alone does not have a significant enough
        effect on the mass of a planet to alter its gravitational force
        appreciably.

Hyperion-3.0-Mistral-7B-alpha

Model Details

  • Model Name: Locutusque/Hyperion-3.0-Mistral-7B-alpha
  • Base Model: mistralai/Mistral-7B-v0.1
  • Publisher: Locutusque
  • Model Type: Question answering, conversational AI, code generation, medical text comprehension, mathematical reasoning, logical reasoning.
  • Language: Multi-domain, English language.
  • License: Apache-2.0

Model Description

Locutusque/Hyperion-3.0-Mistral-7B-alpha is a state-of-the-art language model fine-tuned on the Hyperion-v3.0 dataset for advanced reasoning across scientific domains. This model is designed to handle complex inquiries and instructions, leveraging the diverse and rich information contained in the Hyperion dataset. Its primary use cases include but are not limited to complex question answering, conversational understanding, code generation, medical text comprehension, mathematical reasoning, and logical reasoning. This model is designed to greatly outperform its predecessors.

Intended Use

This model is intended for researchers and practitioners looking for a powerful tool to tackle challenging problems in scientific domains. It can be used in the following scenarios:

  • AI-driven tutoring systems for science, medicine, mathematics, and computer science.
  • Assistive tools for professionals requiring fast and accurate domain-specific information retrieval.
  • Platforms that require conversational AI capabilities with a focus on technical and scientific reasoning.
  • Automation in code generation and understanding complex programming context.

Training Data

The Locutusque/Hyperion-3.0-Mistral-7B-alpha model was fine-tuned on 200,000 examples of the Hyperion-3.0 dataset, which amalgamates various datasets rich in diversity and complexity, including programming, medical texts, mathematical problems, and reasoning tasks.

Quants

ExLlamaV2: https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-exl2

GGUF: https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-alpha-GGUF

Evaluation Results

Zero-shot AGIEval

Tasks Version Filter n-shot Metric Value Stderr
agieval_nous N/A none None acc_norm 0.3500 ± 0.0092
none None acc 0.3519 ± 0.0093
- agieval_aqua_rat 1 none None acc 0.2087 ± 0.0255
none None acc_norm 0.2165 ± 0.0259
- agieval_logiqa_en 1 none None acc 0.3164 ± 0.0182
none None acc_norm 0.3533 ± 0.0187
- agieval_lsat_ar 1 none None acc 0.2348 ± 0.0280
none None acc_norm 0.2174 ± 0.0273
- agieval_lsat_lr 1 none None acc 0.3529 ± 0.0212
none None acc_norm 0.3647 ± 0.0213
- agieval_lsat_rc 1 none None acc 0.4721 ± 0.0305
none None acc_norm 0.4201 ± 0.0301
- agieval_sat_en 1 none None acc 0.6019 ± 0.0342
none None acc_norm 0.6117 ± 0.0340
- agieval_sat_en_without_passage 1 none None acc 0.4078 ± 0.0343
none None acc_norm 0.3835 ± 0.0340
- agieval_sat_math 1 none None acc 0.3091 ± 0.0312
none None acc_norm 0.2364 ± 0.0287

5 shot CoT MMLU

Tasks Version Filter n-shot Metric Value Stderr
mmlu_flan_cot_fewshot N/A get-answer 0 exact_match 0.5924 ± 0.0118
- mmlu_flan_cot_fewshot_humanities N/A get-answer 0 exact_match 0.5077 ± 0.0206
- mmlu_flan_cot_fewshot_formal_logic 0 get-answer 0 exact_match 0.2143 ± 0.1138
- mmlu_flan_cot_fewshot_high_school_european_history 0 get-answer 0 exact_match 0.6111 ± 0.1182
- mmlu_flan_cot_fewshot_high_school_us_history 0 get-answer 0 exact_match 0.7727 ± 0.0914
- mmlu_flan_cot_fewshot_high_school_world_history 0 get-answer 0 exact_match 0.6154 ± 0.0973
- mmlu_flan_cot_fewshot_international_law 0 get-answer 0 exact_match 0.9231 ± 0.0769
- mmlu_flan_cot_fewshot_jurisprudence 0 get-answer 0 exact_match 0.3636 ± 0.1521
- mmlu_flan_cot_fewshot_logical_fallacies 0 get-answer 0 exact_match 0.7222 ± 0.1086
- mmlu_flan_cot_fewshot_moral_disputes 0 get-answer 0 exact_match 0.5526 ± 0.0817
- mmlu_flan_cot_fewshot_moral_scenarios 0 get-answer 0 exact_match 0.3900 ± 0.0490
- mmlu_flan_cot_fewshot_philosophy 0 get-answer 0 exact_match 0.7647 ± 0.0738
- mmlu_flan_cot_fewshot_prehistory 0 get-answer 0 exact_match 0.7143 ± 0.0775
- mmlu_flan_cot_fewshot_professional_law 0 get-answer 0 exact_match 0.3471 ± 0.0366
- mmlu_flan_cot_fewshot_world_religions 0 get-answer 0 exact_match 0.8947 ± 0.0723
- mmlu_flan_cot_fewshot_other N/A get-answer 0 exact_match 0.6921 ± 0.0240
- mmlu_flan_cot_fewshot_business_ethics 0 get-answer 0 exact_match 0.9091 ± 0.0909
- mmlu_flan_cot_fewshot_clinical_knowledge 0 get-answer 0 exact_match 0.5517 ± 0.0940
- mmlu_flan_cot_fewshot_college_medicine 0 get-answer 0 exact_match 0.7727 ± 0.0914
- mmlu_flan_cot_fewshot_global_facts 0 get-answer 0 exact_match 0.6000 ± 0.1633
- mmlu_flan_cot_fewshot_human_aging 0 get-answer 0 exact_match 0.6522 ± 0.1015
- mmlu_flan_cot_fewshot_management 0 get-answer 0 exact_match 0.9091 ± 0.0909
- mmlu_flan_cot_fewshot_marketing 0 get-answer 0 exact_match 0.8400 ± 0.0748
- mmlu_flan_cot_fewshot_medical_genetics 0 get-answer 0 exact_match 1.0000 ± 0.0000
- mmlu_flan_cot_fewshot_miscellaneous 0 get-answer 0 exact_match 0.7791 ± 0.0450
- mmlu_flan_cot_fewshot_nutrition 0 get-answer 0 exact_match 0.6667 ± 0.0833
- mmlu_flan_cot_fewshot_professional_accounting 0 get-answer 0 exact_match 0.4194 ± 0.0901
- mmlu_flan_cot_fewshot_professional_medicine 0 get-answer 0 exact_match 0.6774 ± 0.0853
- mmlu_flan_cot_fewshot_virology 0 get-answer 0 exact_match 0.3889 ± 0.1182
- mmlu_flan_cot_fewshot_social_sciences N/A get-answer 0 exact_match 0.6973 ± 0.0239
- mmlu_flan_cot_fewshot_econometrics 0 get-answer 0 exact_match 0.3333 ± 0.1421
- mmlu_flan_cot_fewshot_high_school_geography 0 get-answer 0 exact_match 0.9091 ± 0.0627
- mmlu_flan_cot_fewshot_high_school_government_and_politics 0 get-answer 0 exact_match 0.8095 ± 0.0878
- mmlu_flan_cot_fewshot_high_school_macroeconomics 0 get-answer 0 exact_match 0.6279 ± 0.0746
- mmlu_flan_cot_fewshot_high_school_microeconomics 0 get-answer 0 exact_match 0.6154 ± 0.0973
- mmlu_flan_cot_fewshot_high_school_psychology 0 get-answer 0 exact_match 0.9167 ± 0.0360
- mmlu_flan_cot_fewshot_human_sexuality 0 get-answer 0 exact_match 0.5000 ± 0.1508
- mmlu_flan_cot_fewshot_professional_psychology 0 get-answer 0 exact_match 0.6667 ± 0.0572
- mmlu_flan_cot_fewshot_public_relations 0 get-answer 0 exact_match 0.5833 ± 0.1486
- mmlu_flan_cot_fewshot_security_studies 0 get-answer 0 exact_match 0.4444 ± 0.0975
- mmlu_flan_cot_fewshot_sociology 0 get-answer 0 exact_match 0.7727 ± 0.0914
- mmlu_flan_cot_fewshot_us_foreign_policy 0 get-answer 0 exact_match 0.7273 ± 0.1408
- mmlu_flan_cot_fewshot_stem N/A get-answer 0 exact_match 0.5164 ± 0.0265
- mmlu_flan_cot_fewshot_abstract_algebra 0 get-answer 0 exact_match 0.4545 ± 0.1575
- mmlu_flan_cot_fewshot_anatomy 0 get-answer 0 exact_match 0.3571 ± 0.1329
- mmlu_flan_cot_fewshot_astronomy 0 get-answer 0 exact_match 0.5000 ± 0.1291
- mmlu_flan_cot_fewshot_college_biology 0 get-answer 0 exact_match 0.5625 ± 0.1281
- mmlu_flan_cot_fewshot_college_chemistry 0 get-answer 0 exact_match 0.3750 ± 0.1830
- mmlu_flan_cot_fewshot_college_computer_science 0 get-answer 0 exact_match 0.2727 ± 0.1408
- mmlu_flan_cot_fewshot_college_mathematics 0 get-answer 0 exact_match 0.2727 ± 0.1408
- mmlu_flan_cot_fewshot_college_physics 0 get-answer 0 exact_match 0.4545 ± 0.1575
- mmlu_flan_cot_fewshot_computer_security 0 get-answer 0 exact_match 0.7273 ± 0.1408
- mmlu_flan_cot_fewshot_conceptual_physics 0 get-answer 0 exact_match 0.6154 ± 0.0973
- mmlu_flan_cot_fewshot_electrical_engineering 0 get-answer 0 exact_match 0.6875 ± 0.1197
- mmlu_flan_cot_fewshot_elementary_mathematics 0 get-answer 0 exact_match 0.7317 ± 0.0701
- mmlu_flan_cot_fewshot_high_school_biology 0 get-answer 0 exact_match 0.7188 ± 0.0808
- mmlu_flan_cot_fewshot_high_school_chemistry 0 get-answer 0 exact_match 0.3636 ± 0.1050
- mmlu_flan_cot_fewshot_high_school_computer_science 0 get-answer 0 exact_match 0.6667 ± 0.1667
- mmlu_flan_cot_fewshot_high_school_mathematics 0 get-answer 0 exact_match 0.4138 ± 0.0931
- mmlu_flan_cot_fewshot_high_school_physics 0 get-answer 0 exact_match 0.2353 ± 0.1060
- mmlu_flan_cot_fewshot_high_school_statistics 0 get-answer 0 exact_match 0.4348 ± 0.1057
- mmlu_flan_cot_fewshot_machine_learning 0 get-answer 0 exact_match 0.3636 ± 0.1521
Groups Version Filter n-shot Metric Value Stderr
mmlu_flan_cot_fewshot N/A get-answer 0 exact_match 0.5924 ± 0.0118
- mmlu_flan_cot_fewshot_humanities N/A get-answer 0 exact_match 0.5077 ± 0.0206
- mmlu_flan_cot_fewshot_other N/A get-answer 0 exact_match 0.6921 ± 0.0240
- mmlu_flan_cot_fewshot_social_sciences N/A get-answer 0 exact_match 0.6973 ± 0.0239
- mmlu_flan_cot_fewshot_stem N/A get-answer 0 exact_match 0.5164 ± 0.0265

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Locutusque/Hyperion-3.0-Mistral-7B-alpha"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# For a text generation task
input_text = "<|im_start|>user\nWhat are the implications of Einstein's theory of relativity in modern physics?<|im_end|>\n<|im_start|>assistant\n"
input_ids = tokenizer.encode(input_text, return_tensors="pt")

# Generate a response
outputs = model.generate(input_ids, max_length=200, num_return_sequences=1, temperature=0.8, top_p=0.95, top_k=40, repetition_penalty=1.1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Known Limitations

The diversity of the dataset could lead to inconsistencies in the model's responses due to variations in data formatting and annotation quality.

This model is also very compliant, it will respond to any request. Please make sure to build upon this model with DPO if you plan on using it for enterprise-level deployment.

Licensing Information

This model is released under the Apache-2.0 license.