| <strong style="font-size: 24px;">"My name is Epicurus, but my friends call me "Epic" for short. "<strong style="font-size: 24px;"></strong>. | |
| <strong style="font-size: 24px;">SageBeluga13B</strong> Stoic assistant fine-tuned by <strong style="font-size: 24px;">dscompounding.com</strong>. | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/645ba35bbc7518912e2135e6/iAd3EFZptpoE8QzZKnaxT.png" alt="Dave86CH_epic_badass_marcus_aurelius_fighting_0c2c720e-bcff-471e-9a05-89aecb45722a.png" width="500"> | |
| Marcus Aurelius | |
| # SageBeluga13 Model README | |
| ## Description | |
| The `SageBeluga13` model, hosted on Hugging Face, has been fine-tuned for specific tasks. | |
| To utilize this model: | |
| ```python | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| import transformers | |
| import torch | |
| model = "davesoma/SageBeluga13" | |
| tokenizer = AutoTokenizer.from_pretrained(model) | |
| pipeline = transformers.pipeline( | |
| "text-generation", | |
| model=model, | |
| tokenizer=tokenizer, | |
| torch_dtype=torch.float32 | |
| ) | |
| sequences = pipeline( | |
| "Girafatron is obsessed with giraffes...", | |
| max_length=200, | |
| do_sample=True, | |
| top_k=10, | |
| num_return_sequences=1, | |
| eos_token_id=tokenizer.eos_token_id | |
| ) | |
| for seq in sequences: | |
| print(f"Result: {seq['generated_text']}") | |
| ``` | |
| ## Example | |
| ![SageBeluga13B.jpg]() | |
| <img src="https://cdn-uploads.huggingface.co/production/uploads/645ba35bbc7518912e2135e6/UZLw9vkVCc2nQ56jxVZ4y.jpeg" alt="SageBeluga13.png" width="800"> | |
| ## Past experiments | |
| https://dscompounding.com/2023/03/31/chapter-iii-digital-marcus-aurelius/ | |