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")
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

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
```

translation catalan english

#15

by Vector333 - opened Mar 23

Discussion

Vector333

Mar 23

•

edited Mar 23

I use this model to translate construction element names from catalan to english. The names are available as strings in the form:

MaoCalat_15cm

which corresponds to:

Mao = brick https://ca.wikipedia.org/wiki/Ma%C3%B3_(construcci%C3%B3)
Calat = perforated https://ca.wikipedia.org/wiki/Calat_(decoraci%C3%B3)

The TA model just returns the original string, probably due to being trained on text, not strings of that format. I.e. it seems to lack the flexibility to generalize to non-fluid text, shortcuts, underscores and other formats commonly used as descriptors.
The conversational model seems to performs better, but does not handle catalan sufficiently well enough to understand this translation.

--- Mao Calat 15cm ---
Translation: Element name: Mao Calat 15cm

Other questionable performances are reflected in:

--- Massissa 35cm ---
Translation: Element name: Massive 35 cm
--- Mur Pantalla Formigo Armat 500mm ---
Translation: English translation: Screen Wall Formigo Armature 500 mm
--- Mur Formigo Armat 250mm ---
Translation: Element name: Wall Formigo Armat 250mm

To mention some success cases:
--- Divisoria Guix Laminat Triple Placa 160mm ---
Translation: English translation: Gypsum Board Triple Layer 160mm
--- Facana Peces Ceramiques Aillament 100mm ---
Translation: Element name: Facade ceramic insulation 100mm
--- Xapa Grecada Aillament 210mm ---
Translation: Xapa Grecada Aillament 210mm - Sheet Greca Insulation 210mm

How could this be improved?

best regards

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