Instructions to use JosephusCheung/Guanaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JosephusCheung/Guanaco with Transformers:

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

pipe = pipeline("text-generation", model="JosephusCheung/Guanaco")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JosephusCheung/Guanaco")
model = AutoModelForCausalLM.from_pretrained("JosephusCheung/Guanaco", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JosephusCheung/Guanaco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JosephusCheung/Guanaco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JosephusCheung/Guanaco",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JosephusCheung/Guanaco

SGLang

How to use JosephusCheung/Guanaco 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 "JosephusCheung/Guanaco" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JosephusCheung/Guanaco",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "JosephusCheung/Guanaco" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JosephusCheung/Guanaco",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JosephusCheung/Guanaco with Docker Model Runner:
```
docker model run hf.co/JosephusCheung/Guanaco
```

JosephusCheung commited on Apr 19, 2023

Commit

4d44ce2

1 Parent(s): e233149

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -30,7 +30,7 @@ Guanaco is an advanced instruction-following language model built on Meta's LLaM
 In an effort to foster openness and replicability in research, we have made the Guanaco Dataset publicly accessible and we have released the model weights here. By providing these resources, we aim to inspire more researchers to pursue related research and collectively advance the development of instruction-following language models.
-[KBlueLeaf](https://huggingface.co/KBlueLeaf)’s invaluable contributions to the conceptual validation, [trained model](https://huggingface.co/KBlueLeaf/guanaco-7B-leh) and [inference development](https://github.com/KohakuBlueleaf/guanaco-lora) of the model are gratefully acknowledged, without whose efforts this project would not have come to fruition.
 When utilizing the Guanaco model, please bear in mind the following points:

 In an effort to foster openness and replicability in research, we have made the Guanaco Dataset publicly accessible and we have released the model weights here. By providing these resources, we aim to inspire more researchers to pursue related research and collectively advance the development of instruction-following language models.
+[KBlueLeaf](https://huggingface.co/KBlueLeaf)’s invaluable contributions to the conceptual validation, [trained model](https://huggingface.co/KBlueLeaf/guanaco-7B-leh) and [inference development](https://github.com/KohakuBlueleaf/guanaco-lora) of the model would be gratefully acknowledged, without whose efforts the project shall never have come to fruition.
 When utilizing the Guanaco model, please bear in mind the following points: