Views
No views yet
M4-ai/hyperion-medium-preview is a state-of-the-art language model fine-tuned on the Hyperion 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.M4-ai/hyperion-medium-preview 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.1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_name = "M4-ai/hyperion-medium-preview"
4tokenizer = AutoTokenizer.from_pretrained(model_name)
5model = AutoModelForCausalLM.from_pretrained(model_name)
6
7# For a text generation task
8input_text = "<|im_start|>user\nWhat are the implications of Einstein's theory of relativity in modern physics?<|im_end|>\n<|im_start|>assistant\n"
9input_ids = tokenizer.encode(input_text, return_tensors="pt")
10
11# Generate a response
12outputs = 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)
13print(tokenizer.decode(outputs[0], skip_special_tokens=True))@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}
}| 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 |