Instructions to use SIRIS-Lab/impuls-salamandra-7b-query-parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SIRIS-Lab/impuls-salamandra-7b-query-parser with Transformers:

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

pipe = pipeline("text-generation", model="SIRIS-Lab/impuls-salamandra-7b-query-parser")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SIRIS-Lab/impuls-salamandra-7b-query-parser")
model = AutoModelForCausalLM.from_pretrained("SIRIS-Lab/impuls-salamandra-7b-query-parser")
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 SIRIS-Lab/impuls-salamandra-7b-query-parser with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/SIRIS-Lab/impuls-salamandra-7b-query-parser

SGLang

How to use SIRIS-Lab/impuls-salamandra-7b-query-parser 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 "SIRIS-Lab/impuls-salamandra-7b-query-parser" \
    --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": "SIRIS-Lab/impuls-salamandra-7b-query-parser",
		"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 "SIRIS-Lab/impuls-salamandra-7b-query-parser" \
        --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": "SIRIS-Lab/impuls-salamandra-7b-query-parser",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SIRIS-Lab/impuls-salamandra-7b-query-parser with Docker Model Runner:
```
docker model run hf.co/SIRIS-Lab/impuls-salamandra-7b-query-parser
```

PabloAccuosto commited on Dec 10, 2025

Commit

a6e8ece

verified ·

1 Parent(s): 91261b2

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +8 -2

README.md CHANGED Viewed

@@ -19,6 +19,8 @@ tags:
   - fine-tuned
   - AINA
   - R&D
 metrics:
   - accuracy
 model-index:
@@ -111,12 +113,15 @@ projectes d'IA en salut finançats per H2020 des de 2020
 | Warmup ratio | 0.1 |
 ### Training Data
-- **Size**: 682 multilingual queries (synthetic, template-generated)
 - **Language distribution**: ~33% Catalan, ~33% Spanish, ~33% English
 - **Query types**: Discover (88%), Quantify (12%)
 ### Evaluation Data
-- **Size**: 100 real queries from domain experts (SIRIS Academic)
 - **Annotation**: Manual gold-standard JSON for each query
 ## Evaluation Results
@@ -305,6 +310,7 @@ This model is released under the [Apache 2.0 License](https://www.apache.org/lic
 ## Links
 - **Project Repository**: [github.com/sirisacademic/aina-impulse](https://github.com/sirisacademic/aina-impulse)
 - **Base Model**: [BSC-LT/salamandra-7b-instruct-tools](https://huggingface.co/BSC-LT/salamandra-7b-instruct-tools)
 - **AINA Project**: [projecteaina.cat](https://projecteaina.cat/)

   - fine-tuned
   - AINA
   - R&D
+datasets:
+  - SIRIS-Lab/impuls-query-parsing
 metrics:
   - accuracy
 model-index:
 | Warmup ratio | 0.1 |
 ### Training Data
+- **Dataset**: [SIRIS-Lab/impuls-query-parsing](https://huggingface.co/datasets/SIRIS-Lab/impuls-query-parsing)
+- **Training split**: 682 multilingual queries (synthetic, template-generated)
 - **Language distribution**: ~33% Catalan, ~33% Spanish, ~33% English
 - **Query types**: Discover (88%), Quantify (12%)
 ### Evaluation Data
+- **Test split**: 100 real queries from domain experts (SIRIS Academic)
 - **Annotation**: Manual gold-standard JSON for each query
 ## Evaluation Results
 ## Links
+- **Training Dataset**: [SIRIS-Lab/impuls-query-parsing](https://huggingface.co/datasets/SIRIS-Lab/impuls-query-parsing)
 - **Project Repository**: [github.com/sirisacademic/aina-impulse](https://github.com/sirisacademic/aina-impulse)
 - **Base Model**: [BSC-LT/salamandra-7b-instruct-tools](https://huggingface.co/BSC-LT/salamandra-7b-instruct-tools)
 - **AINA Project**: [projecteaina.cat](https://projecteaina.cat/)