Instructions to use Cartinoe5930/vicuna-orac with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cartinoe5930/vicuna-orac with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Cartinoe5930/vicuna-orac")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Cartinoe5930/vicuna-orac")
model = AutoModelForCausalLM.from_pretrained("Cartinoe5930/vicuna-orac", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Cartinoe5930/vicuna-orac with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cartinoe5930/vicuna-orac"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cartinoe5930/vicuna-orac",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Cartinoe5930/vicuna-orac

SGLang

How to use Cartinoe5930/vicuna-orac 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 "Cartinoe5930/vicuna-orac" \
    --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": "Cartinoe5930/vicuna-orac",
		"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 "Cartinoe5930/vicuna-orac" \
        --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": "Cartinoe5930/vicuna-orac",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Cartinoe5930/vicuna-orac with Docker Model Runner:
```
docker model run hf.co/Cartinoe5930/vicuna-orac
```

vicuna-orac

vicuna-orac is a merge of the following models using LazyMergekit:

🧩 Configuration

models:
  - model: lmsys/vicuna-13b-v1.5
    parameters:
      weight: 0.5
  - model: OpenAssistant/llama2-13b-orca-8k-3319
    parameters:
      weight: 0.5
merge_method: linear
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Cartinoe5930/vicuna-orac"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 8

Safetensors

Model size

13B params

Tensor type

BF16

Model tree for Cartinoe5930/vicuna-orac

OpenAssistant/llama2-13b-orca-8k-3319

lmsys/vicuna-13b-v1.5

Merge model

this model