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

Libraries

How to use NLPnorth/snakmodel-7b-instruct with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NLPnorth/snakmodel-7b-instruct")
model = AutoModelForCausalLM.from_pretrained("NLPnorth/snakmodel-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NLPnorth/snakmodel-7b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NLPnorth/snakmodel-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": "NLPnorth/snakmodel-7b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NLPnorth/snakmodel-7b-instruct

SGLang

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

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

personads commited on Oct 18, 2024

Commit

0ad3fed

verified ·

1 Parent(s): 1815ae7

added library to metadata

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -5,12 +5,13 @@ license: llama2
 base_model:
 - NLPnorth/snakmodel-7b-base
 pipeline_tag: text-generation
 ---
 ![SnakModel Instruct Logo](snakmodel.png)
 ## Model Details
-**SnakModel** is a 7B-parameter model specifically designed for the Danish language. This is the instruction-tuned variant: `SnakModel-7B (instruct)`. Our models builds upon [Llama 2](https://huggingface.co/meta-llama/Llama-2-7b-hf), which we continuously pre-train on a diverse collection of Danish corpora comprising 350M documents and 13.6B words, before tuning it on 3.7M Danish instruction-answer pairs.
 **Model Developers**
@@ -22,7 +23,7 @@ SnakModel comes as an instruction-tuned, and a base version. In addition, each m
 **Input**
-Text only.
 **Output**

 base_model:
 - NLPnorth/snakmodel-7b-base
 pipeline_tag: text-generation
+library_name: transformers
 ---
 ![SnakModel Instruct Logo](snakmodel.png)
 ## Model Details
+**SnakModel** is a 7B-parameter model specifically designed for the Danish language. This is the instruction-tuned variant: `SnakModel-7B (instruct)`. Our models build upon [Llama 2](https://huggingface.co/meta-llama/Llama-2-7b-hf), which we continuously pre-train on a diverse collection of Danish corpora comprising 350M documents and 13.6B words, before tuning it on 3.7M Danish instruction-answer pairs.
 **Model Developers**
 **Input**
+Text only, with instructions following the `[INST] {instruction} [/INST]` template.
 **Output**