<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:

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/