Locutusque_-_Hyperion-3.0-Mistral-7B-alpha-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Hyperion-3.0-Mistral-7B-alpha - GGUF

• Model creator: https://huggingface.co/Locutusque/
• Original model: https://huggingface.co/Locutusque/Hyperion-3.0-Mistral-7B-alpha/

Original model description:

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

5 shot CoT MMLU

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.