Instructions to use Salesforce/xLAM-v0.1-r with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Salesforce/xLAM-v0.1-r with Transformers:

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

pipe = pipeline("text-generation", model="Salesforce/xLAM-v0.1-r")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Salesforce/xLAM-v0.1-r")
model = AutoModelForCausalLM.from_pretrained("Salesforce/xLAM-v0.1-r")
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-v0.1-r with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Salesforce/xLAM-v0.1-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-v0.1-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Salesforce/xLAM-v0.1-r

SGLang

How to use Salesforce/xLAM-v0.1-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-v0.1-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-v0.1-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-v0.1-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-v0.1-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Salesforce/xLAM-v0.1-r with Docker Model Runner:
```
docker model run hf.co/Salesforce/xLAM-v0.1-r
```

jianguozhang commited on Mar 18, 2024

Commit

3a00587

verified ·

1 Parent(s): 7736355

Upload 2 files

Browse files

Files changed (2) hide show

README.md +13 -0
xlam-no-background.png +0 -0

README.md CHANGED Viewed

@@ -1,3 +1,16 @@
 ---
 license: apache-2.0
 ---

 ---
 license: apache-2.0
 ---
+<div align="center">
+<img src="https://huggingface.co/Salesforce/xLAM-v0.1/resolve/main/xlam-no-background.png"
+alt="drawing" width="510"/>
+</div>
+GitHub: https://github.com/SalesforceAIResearch/xLAM
+Paper: https://arxiv.org/abs/2402.15506
+License: apache-2.0
+If you already know [Mixtral](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1), xLAM-v0.1 is a significant upgrade and better at many things. For the same number of parameters, the model have been fine-tuned across a wide range of agent tasks and scenarios, all while preserving the capabilities of the original model.

xlam-no-background.png ADDED Viewed