Instructions to use Salesforce/xLAM-8x7b-r with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/xLAM-8x7b-r with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/xLAM-8x7b-r")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/xLAM-8x7b-r")
model = AutoModelForCausalLM.from_pretrained("Salesforce/xLAM-8x7b-r", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Salesforce/xLAM-8x7b-r with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/xLAM-8x7b-r"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Salesforce/xLAM-8x7b-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Salesforce/xLAM-8x7b-r

SGLang

How to use Salesforce/xLAM-8x7b-r 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 "Salesforce/xLAM-8x7b-r" \
    --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": "Salesforce/xLAM-8x7b-r",
		"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 "Salesforce/xLAM-8x7b-r" \
        --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": "Salesforce/xLAM-8x7b-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Salesforce/xLAM-8x7b-r with Docker Model Runner:
```
docker model run hf.co/Salesforce/xLAM-8x7b-r
```

Add ActionStudio paper and library_name

by nielsr HF Staff - opened Mar 31, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+37

-15

nielsr

Mar 31, 2025

This PR ensures the model card mentions the ActionStudio paper and adds library_name: transformers to the model card. This will make the "how to use" button available on the top right, making it
easier to use this model for other people.

Add ActionStudio paper and library_name6c3090a3

jianguozhang changed pull request status to merged Apr 1, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment