Instructions to use davesoma/SageBeluga13 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use davesoma/SageBeluga13 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="davesoma/SageBeluga13")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("davesoma/SageBeluga13") model = AutoModelForCausalLM.from_pretrained("davesoma/SageBeluga13") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use davesoma/SageBeluga13 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "davesoma/SageBeluga13" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "davesoma/SageBeluga13", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/davesoma/SageBeluga13
- SGLang
How to use davesoma/SageBeluga13 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "davesoma/SageBeluga13" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "davesoma/SageBeluga13", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "davesoma/SageBeluga13" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "davesoma/SageBeluga13", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use davesoma/SageBeluga13 with Docker Model Runner:
docker model run hf.co/davesoma/SageBeluga13
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
"My name is Epicurus, but my friends call me "Epic" for short. ".
SageBeluga13B Stoic assistant fine-tuned by dscompounding.com.
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
Past experiments
https://dscompounding.com/2023/03/31/chapter-iii-digital-marcus-aurelius/
- Downloads last month
- 4