Instructions to use marcuscedricridia/olmner-della-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use marcuscedricridia/olmner-della-7b with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("marcuscedricridia/olmner-della-7b")
model = AutoModelForCausalLM.from_pretrained("marcuscedricridia/olmner-della-7b")
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 marcuscedricridia/olmner-della-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/marcuscedricridia/olmner-della-7b

SGLang

How to use marcuscedricridia/olmner-della-7b 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 "marcuscedricridia/olmner-della-7b" \
    --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": "marcuscedricridia/olmner-della-7b",
		"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 "marcuscedricridia/olmner-della-7b" \
        --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": "marcuscedricridia/olmner-della-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use marcuscedricridia/olmner-della-7b with Docker Model Runner:
```
docker model run hf.co/marcuscedricridia/olmner-della-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

📊 OLMNER-DELLA-7B Benchmark Results

OLMNER-DELLA-7B takes OLMNER to the next level by merging it with a DELLA-optimized model, achieving even stronger results!

🔥 Performance Scores

Metric	Score
Average Score	36.35%
IFEval	76.37%
BBH	35.90%
MATH	49.62%
GPQA	6.82%
MUSR	11.80%
MMLU-PRO	37.62%

🌍 Carbon Emission Estimate: 0.65 kg CO₂

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ehristoforu/fq2.5-7b-it-normalize_false
    #no parameters necessary for base model
  - model: Etherll/Qwen2.5-7B-della-test
    parameters:
      density: 0.5
      weight: 0.5
  - model: marcuscedricridia/olmner-7b
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: ehristoforu/fq2.5-7b-it-normalize_false
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for marcuscedricridia/olmner-della-7b

Etherll/Qwen2.5-7B-della-test

ehristoforu/fq2.5-7b-it-normalize_false

marcuscedricridia/olmner-7b

Merge model

this model

Merges

4 models

Quantizations

2 models