BSC-LT/salamandra-7b-instruct-tools-16k

WARNING: This is a language model that has undergone instruction tuning for conversational settings that exploit function calling capabilities. It has not been aligned with human preferences. As a result, it may generate outputs that are inappropriate, misleading, biased, or unsafe. These risks can be mitigated through additional post-training stages, which is strongly recommended before deployment in any production system, especially for high-stakes applications.

How to use

from datetime import datetime
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "BSC-LT/salamandra-7b-instruct"

text = "What is the weather like in Paris today?"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.bfloat16
  )

message = [ { "role": "user", "content": text } ]

tools = [{
    "type": "function",
    "name": "get_weather",
    "description": "Get current temperature for a given location.",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {
                "type": "string",
                "description": "City and country e.g. Bogotá, Colombia"
            }
        },
        "required": [
            "location"
        ],
        "additionalProperties": False
    }
}]


prompt = tokenizer.apply_chat_template(
    message,
    tokenize=False,
    add_generation_prompt=True,
    tools=tools
)

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=1000)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Output:

<tool_call>
{"name": "get_weather", "arguments": {"location": "Paris, France"}}
</tool_call>

Deploy with vllm

Deploy the model using vllm docker image.

docker run --runtime nvidia --gpus all \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HUGGING_FACE_HUB_TOKEN=<secret>" \
    -p 80:80 \
    vllm/vllm-openai:latest \
    --model BSC-LT/salamandra-7b-instruct-tools \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --max_model_len 8196 \
    --port 80

Then use it with openai api

pip install openai

from openai import OpenAI
client = OpenAI(
        base_url="http://localhost:8080/v1/", 
        api_key="hf_xxxx"
    )

models = client.models.list()
model = models.data[0].id

system_message = ""
messages = [{ "role": "system", "content": system_message}] if system_message else []
messages.append( {"role":"user", "content": "What is the weather like in Paris today?"})
print(messages)
chat_completion = client.chat.completions.create(
    model=model,
    tools=tools
    messages=messages,
    stream=False,
    max_tokens=1000,
    temperature=0.1,
    frequency_penalty=0.2,
)

msg = chat_completion.choices[0].message

# --- HANDLE TOOL CALL OR NORMAL CONTENT ---

if not getattr(msg, "tool_calls", None):
    # Normal assistant message
    print(msg.content)

    messages.append({
        "role": "assistant",
        "content": msg.content
    })

else:
    # Assistant tool call message
    print(msg.tool_calls)

    messages.append({"role": "assistant", "tool_calls": msg.tool_calls})

    # --- Fake tool execution example ---
    tool_call = msg.tool_calls[0]
    # Example: handle the get_weather tool
    if tool_call.function.name == "get_weather":
        # Fake tool result (this would come from your actual backend)
        fake_tool_result = '{"temperature": 18, "unit": "C", "description": "Partly cloudy in Paris"}'

        # Append the tool result message so the model can use it in the next turn
        messages.append({
            "role": "tool",
            "tool_call_id": tool_call.id,
            "name": tool_call.function.name,
            "content": fake_tool_result,
        })