README.md

metadata

library_name: transformers
license: apache-2.0
language:
  - en
widget:
  - example_title: Reasoning
    text: >
      <|im_start|>system

      You are Hyperion, an AI assistant developed by Sebastian Gabarain with a
      focus in reasoning, coding, science, and other general-purpose subjects.
      You are an AI assistant that follows instruction extremely well. Help as
      much as you can.

      <|im_end|>

      <|im_start|>user

      In this task, you are given a description of an object and its
      surroundings. Your

      task is to describe the motion of the object mentioned in the description
      using

      differential equations. The answer should be a mathematical expression in
      t. Description:

      A ball is thrown up at 30 ft/sec from 3 feet off the ground. Solve this
      step-by-step,

      explaining each step in detail.

      <|im_end|>

      <|im_start|>assistant
    output:
      text: >
        Hyperion here. The task requires you to describe the motion of a ball
        thrown up using differential equations. Here's the detailed explanation
        of how to solve it:


        1. Identify the given information:
           - Initial velocity (v0): 30 ft/sec
           - Initial height (y0): 3 feet off the ground

        2. Determine the acceleration due to gravity (g) at sea level, which is
        approximately -32.2 ft/s^2. Since we're dealing with a short distance
        and not very high altitudes, we can consider this value of g as
        constant.


        3. Use Newton's second law of motion to find the differential equation
        that describes the motion:
           - The net force acting on the ball is the sum of gravity (mg) and air resistance (which we will neglect for simplicity). So, Fnet = mg.
           - Since acceleration equals force divided by mass, a = Fnet/m. In this case, m cancels out, so a = g.
           - The motion equation becomes: dv/dt = g = -32.2 ft/s^2 (since we're moving upwards). This is the first differential equation.

        4. Since we want to describe the ball's position (y) as well, we need
        another differential equation. We can use kinematics equations:
           - The velocity equation is v = v0 + at. Substitute the value of a from step 3:
             dv/dt = -32.2 ft/s^2. Rewriting it as an integral:
              ∫dv = -32.2 ft/s^2 * dt
           - Integrating with respect to time, we get v(t) = -16.1 t + C (constant of integration).

        5. Now we have two equations, one for velocity and another for position:
           - dv/dt = -32.2 ft/s^2 (equation 1)
           - v(t) = -16.1 t + C (equation 2)

        6. We need to find the constant C using the initial conditions given in
        the problem. We know that initially, at time t=0, the ball's velocity is
        v0:
           - Equation 2 becomes v0 = -16.1 * 0 + C, which simplifies to C = v0 = 30 ft/sec (initial velocity).

        7. Now we have both equations with the constants filled in:
           - dv/dt = -32.2 ft/s^2 (equation 1)
           - v(t) = -16.1 t + 30 ft/sec (equation 2)

        8. Finally, we need to find the ball's position (y) as a function of
        time:
           - Use the second kinematics equation y = y0 + v0*t + ½*a*t^2 (since acceleration is constant, it can be moved outside the integral).
           - Substitute the values for v0 and a:
             y(t) = 3 ft + (30 ft/sec) * t + (-½ * 32.2 ft/s^2) * t^2

        That's it! The differential equation describing the motion of the ball
        is:
           - dv/dt = -32.2 ft/s^2 (equation 1)
           - v(t) = -16.1 t + 30 ft/sec (equation 2)
           - y(t) = 3 ft + (30 ft/sec) * t - (16.1 t^2) ft (equation 3)
datasets:
  - Locutusque/hyperion-dpo-v1.0

Hyperion-3.0-Mistral-7B-DPO

Model Details

• Model Name: Locutusque/Hyperion-3.0-Mistral-7B-DPO
• 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-DPO is an advanced language model fine-tuned with a dataset of 20,000 meticulously curated high-quality preference pairs using Direct Preference Optimization (DPO). The examples were generated by GPT-4 to ensure exceptional quality and relevance. This model is designed to provide superior performance across a wide range of complex tasks, including question answering, conversational AI, code generation, medical text comprehension, mathematical reasoning, and logical reasoning.

Intended Use

This model is intended for researchers, developers, and organizations seeking a highly capable and reliable language model for tackling challenging problems across various domains. Potential use cases include:

• Intelligent tutoring systems and educational applications in science, medicine, mathematics, and computer science
• Advanced conversational AI for technical support, customer service, and domain-specific chatbots
• Code generation and analysis tools for software development and programming assistance
• Medical text analysis and information retrieval for healthcare professionals and researchers
• Mathematical problem-solving and logical reasoning applications for academia and industry

Training Data

The Locutusque/Hyperion-3.0-Mistral-7B-DPO model was fine-tuned on a carefully curated dataset of 20,000 preference pairs, where 4,000 examples were used to fine-tune. These examples were generated by GPT-4 to ensure the highest quality and relevance across various domains, including programming, medical texts, mathematical problems, and reasoning tasks. The training data was further optimized using Direct Preference Optimization (DPO) to align the model's outputs with human preferences and improve overall performance.

Quants

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

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

Evaluation Results

mmlu flan cot 5-shot

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
mmlu_flan_cot_fewshot	N/A	get-answer	0	exact_match	0.5833	±	0.0118
- mmlu_flan_cot_fewshot_humanities	N/A	get-answer	0	exact_match	0.5039	±	0.0205
- 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	0.6667	±	0.1143
- 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	0.5385	±	0.0997
- 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	0.5455	±	0.1575
- mmlu_flan_cot_fewshot_logical_fallacies	0	get-answer	0	exact_match	0.7778	±	0.1008
- 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	0.4000	±	0.0492
- 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	0.6571	±	0.0814
- mmlu_flan_cot_fewshot_professional_law	0	get-answer	0	exact_match	0.3294	±	0.0362
- 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	0.6833	±	0.0244
- 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	0.5862	±	0.0931
- mmlu_flan_cot_fewshot_college_medicine	0	get-answer	0	exact_match	0.6364	±	0.1050
- 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	0.6087	±	0.1041
- 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	0.8000	±	0.0816
- 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	0.8023	±	0.0432
- 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	0.4839	±	0.0912
- mmlu_flan_cot_fewshot_professional_medicine	0	get-answer	0	exact_match	0.5806	±	0.0901
- 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	0.7003	±	0.0239
- mmlu_flan_cot_fewshot_econometrics	0	get-answer	0	exact_match	0.4167	±	0.1486
- 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	0.6512	±	0.0735
- mmlu_flan_cot_fewshot_high_school_microeconomics	0	get-answer	0	exact_match	0.5769	±	0.0988
- mmlu_flan_cot_fewshot_high_school_psychology	0	get-answer	0	exact_match	0.9000	±	0.0391
- mmlu_flan_cot_fewshot_human_sexuality	0	get-answer	0	exact_match	0.6667	±	0.1421
- mmlu_flan_cot_fewshot_professional_psychology	0	get-answer	0	exact_match	0.6522	±	0.0578
- 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	0.4074	±	0.0964
- mmlu_flan_cot_fewshot_sociology	0	get-answer	0	exact_match	0.8182	±	0.0842
- 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	0.4866	±	0.0262
- mmlu_flan_cot_fewshot_abstract_algebra	0	get-answer	0	exact_match	0.0909	±	0.0909
- mmlu_flan_cot_fewshot_anatomy	0	get-answer	0	exact_match	0.4286	±	0.1373
- mmlu_flan_cot_fewshot_astronomy	0	get-answer	0	exact_match	0.5625	±	0.1281
- mmlu_flan_cot_fewshot_college_biology	0	get-answer	0	exact_match	0.5000	±	0.1291
- mmlu_flan_cot_fewshot_college_chemistry	0	get-answer	0	exact_match	0.5000	±	0.1890
- 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	0.3636	±	0.1521
- mmlu_flan_cot_fewshot_college_physics	0	get-answer	0	exact_match	0.3636	±	0.1521
- 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	0.6538	±	0.0951
- mmlu_flan_cot_fewshot_electrical_engineering	0	get-answer	0	exact_match	0.7500	±	0.1118
- 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	0.5938	±	0.0882
- 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	0.5556	±	0.1757
- mmlu_flan_cot_fewshot_high_school_mathematics	0	get-answer	0	exact_match	0.3103	±	0.0874
- 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	0.3043	±	0.0981
- mmlu_flan_cot_fewshot_machine_learning	0	get-answer	0	exact_match	0.4545	±	0.1575

Groups	Version	Filter	n-shot	Metric	Value		Stderr
mmlu_flan_cot_fewshot	N/A	get-answer	0	exact_match	0.5833	±	0.0118
- mmlu_flan_cot_fewshot_humanities	N/A	get-answer	0	exact_match	0.5039	±	0.0205
- mmlu_flan_cot_fewshot_other	N/A	get-answer	0	exact_match	0.6833	±	0.0244
- mmlu_flan_cot_fewshot_social_sciences	N/A	get-answer	0	exact_match	0.7003	±	0.0239
- mmlu_flan_cot_fewshot_stem	N/A	get-answer	0	exact_match	0.4866	±	0.0262

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

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

# For a text generation task
input_text = "<|im_start|>user\nExplain the implications of quantum entanglement in layman's terms.<|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, do_sample=True, top_p=0.7, top_k=6) # These are the recommended sample settings.
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Known Limitations

While the training data has been carefully curated and optimized, there may still be some inconsistencies or biases present due to the inherent complexity and diversity of the source dataset. Users should be aware of potential limitations and carefully evaluate the model's outputs for their specific use case.

Additionally, this model is highly compliant and will attempt to respond to most requests. For enterprise-level deployment, it is strongly recommended to further fine-tune the model using DPO to align its behavior with specific requirements and constraints.

Licensing Information

This model is released under the Apache-2.0 license.