Instructions to use BSC-LT/salamandra-2b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BSC-LT/salamandra-2b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="BSC-LT/salamandra-2b-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-2b-instruct")
model = AutoModelForCausalLM.from_pretrained("BSC-LT/salamandra-2b-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 Settings

vLLM

How to use BSC-LT/salamandra-2b-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-2b-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-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BSC-LT/salamandra-2b-instruct

SGLang

How to use BSC-LT/salamandra-2b-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-2b-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-2b-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-2b-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-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BSC-LT/salamandra-2b-instruct with Docker Model Runner:
```
docker model run hf.co/BSC-LT/salamandra-2b-instruct
```

token.json size

by robbiemu - opened Oct 14, 2024

Discussion

robbiemu

Oct 14, 2024

Why is the token.json half the size of the base model's?

joanllop

Oct 15, 2024

•

edited Oct 15, 2024

Hi,

I believe this is because the tokenizer.json file for the instructed models was generated using a version of the tokenizer library prior to this PR: https://github.com/huggingface/tokenizers/pull/909. In contrast, the tokenizer.json files for the base models were created more recently. We believe that the way merge operations are written to the file now causes it to take up twice the space.

For example, what was previously written like this:

"▁profesor a"

is now written like this:
[
"▁profesor",
"a"
]

robbiemu changed discussion status to closed Oct 15, 2024

robbiemu

Oct 15, 2024

•

edited Oct 15, 2024

Just fyi: https://github.com/ollama/ollama/issues/7188#issuecomment-2414666523

Using llama.cpp I didn’t have any issues, but ollama users did.

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