Instructions to use DigitalLearningGmbH/educa-ai-nemo-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DigitalLearningGmbH/educa-ai-nemo-sft with Transformers:

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

pipe = pipeline("text-generation", model="DigitalLearningGmbH/educa-ai-nemo-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DigitalLearningGmbH/educa-ai-nemo-sft")
model = AutoModelForCausalLM.from_pretrained("DigitalLearningGmbH/educa-ai-nemo-sft")
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 DigitalLearningGmbH/educa-ai-nemo-sft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/DigitalLearningGmbH/educa-ai-nemo-sft

SGLang

How to use DigitalLearningGmbH/educa-ai-nemo-sft 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 "DigitalLearningGmbH/educa-ai-nemo-sft" \
    --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": "DigitalLearningGmbH/educa-ai-nemo-sft",
		"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 "DigitalLearningGmbH/educa-ai-nemo-sft" \
        --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": "DigitalLearningGmbH/educa-ai-nemo-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DigitalLearningGmbH/educa-ai-nemo-sft with Docker Model Runner:
```
docker model run hf.co/DigitalLearningGmbH/educa-ai-nemo-sft
```

LenDigLearn commited on Jan 23, 2025

Commit

c5a8a5e

verified ·

1 Parent(s): 1fc3a30

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -62,9 +62,9 @@ Our data encompasses examples of a length up to 16384 tokens, further enhancing
 ## Evaluation
-We performed benchmarks using lighteval. The accuracy numbers obtained this way differ greatly from the base model's official benchmarks and those performed with different benchmark suites.
 Thus, we have run the same benchmarks using lighteval on the [base model](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) under the exact same conditions as well for comparison.
-As of 2025-01-24, We are working on running these benchmarks again using a different suite as well as running more German-specific benchmarks.
 ### English Benchmarks
 | Benchmark | Mistral-Nemo-Instruct 2407 | educa-ai-nemo-sft |

 ## Evaluation
+**IMPORTANT:** We performed benchmarks using lighteval. The accuracy numbers obtained this way differ greatly from the base model's official benchmarks and those performed with different benchmark suites.
 Thus, we have run the same benchmarks using lighteval on the [base model](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) under the exact same conditions as well for comparison.
+**As of 2025-01-24, We are working on running these benchmarks again using a different suite as well as running more German-specific benchmarks.**
 ### English Benchmarks
 | Benchmark | Mistral-Nemo-Instruct 2407 | educa-ai-nemo-sft |