language:
- en
license: apache-2.0
library_name: transformers
model-index:
- name: NeuralHyperion-Medium-Preview
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 60.67
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/NeuralHyperion-Medium-Preview
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 83.67
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/NeuralHyperion-Medium-Preview
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 63.73
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/NeuralHyperion-Medium-Preview
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 42.93
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/NeuralHyperion-Medium-Preview
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 78.53
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/NeuralHyperion-Medium-Preview
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 40.49
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/NeuralHyperion-Medium-Preview
name: Open LLM Leaderboard
Model Card for Locutusque/NeuralHyperion-Medium
Model Details
Model Name: Locutusque/NeuralHyperion-Medium
Base Model: mistralai/Mistral-7B-v0.1
Publisher: M4-ai
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/NeuralHyperion-Medium is a state-of-the-art language model fine-tuned on the Hyperion dataset and further fine-tuned using DPO on Argilla’s orca DPO pairs 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.
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/NeuralHyperion-Medium model was fine-tuned on the Hyperion dataset, which amalgamates various datasets rich in diversity and complexity, including programming, medical texts, mathematical problems, and reasoning tasks. It is then further fine-tuned using DPO on Argilla’s orca DPO pairs to further improve reasoning.
Evaluation Results
Coming soon...
How to Use
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Locutusque/NeuralHyperion-Medium"
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.
Licensing Information
This model is released under the Apache-2.0 license.
Citation Information
If you use Locutusque/NeuralHyperion-Medium in your research, please cite the Hyperion dataset as follows:
@misc{sebastian_gabarain_2024,
title = {Hyperion-1: Illuminating the Path to Advanced Reasoning with a High-Quality, Multidisciplinary Question Answering Dataset},
author = {Sebastian Gabarain},
publisher = {HuggingFace},
year = {2024},
url = {https://huggingface.co/datasets/Locutusque/hyperion-v1.0}
}
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 61.67 |
| AI2 Reasoning Challenge (25-Shot) | 60.67 |
| HellaSwag (10-Shot) | 83.67 |
| MMLU (5-Shot) | 63.73 |
| TruthfulQA (0-shot) | 42.93 |
| Winogrande (5-shot) | 78.53 |
| GSM8k (5-shot) | 40.49 |