Instructions to use BSC-LT/salamandra-7b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BSC-LT/salamandra-7b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="BSC-LT/salamandra-7b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BSC-LT/salamandra-7b-instruct")
model = AutoModelForCausalLM.from_pretrained("BSC-LT/salamandra-7b-instruct", 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 BSC-LT/salamandra-7b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BSC-LT/salamandra-7b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BSC-LT/salamandra-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BSC-LT/salamandra-7b-instruct

SGLang

How to use BSC-LT/salamandra-7b-instruct 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 "BSC-LT/salamandra-7b-instruct" \
    --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": "BSC-LT/salamandra-7b-instruct",
		"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 "BSC-LT/salamandra-7b-instruct" \
        --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": "BSC-LT/salamandra-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BSC-LT/salamandra-7b-instruct with Docker Model Runner:
```
docker model run hf.co/BSC-LT/salamandra-7b-instruct
```

Implement tool calling

by AlbertHerrando - opened Nov 5, 2024

Discussion

AlbertHerrando

Nov 5, 2024

Hello,

I am currently developing GenAI applications with LangChain/LangGraph for the catalan government.

In order to use the Salamandra models in more complex agentic applications we have the need that you implement tool calling to your models.

For more information:
https://python.langchain.com/docs/concepts/tool_calling/

We would appreciate that your models can implement the tool calling standard.

Thank you very much in advance.

luispoveda93

Dec 26, 2024

Hello,

I was also looking for this tool-calling functionality. Avoiding opening another discussion, I'm supporting the urgent necessity of implementing tool calling to be competitive.

Thanks in advance.

Luis Poveda

pauFIB

Mar 19, 2025

Hello,
I am developing a chat agent and would like to express my support in this iniciative. Implementing tool calling would be game changing for the model to be used in both development and production environments.

crodri

Language Technologies Laboratory @ Barcelona Supercomputing Center org Mar 19, 2025

Hi Pau, we are actively implementing tool calling into the Salamandra models but it is still in development, and won't release a fully functional version until later this year. nevertheless, we will open a (again, experimental) ChatUI-like demo shortly for developers to try out that usses Community and BSC tools under the Huggingface formats. We'll keep everyone posted. Thanks

pauFIB

Mar 20, 2025

Hi @crodri ,

Thank you very much for sharing this update; it is very helpful. I appreciate the effort and progress on implementing tool calling, and I look forward to further developments.

Best regards,
Pau Mayench

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