Instructions to use s3nh/Severusectum-7B-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use s3nh/Severusectum-7B-DPO with Transformers:

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

pipe = pipeline("text-generation", model="s3nh/Severusectum-7B-DPO")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("s3nh/Severusectum-7B-DPO")
model = AutoModelForCausalLM.from_pretrained("s3nh/Severusectum-7B-DPO")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use s3nh/Severusectum-7B-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "s3nh/Severusectum-7B-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s3nh/Severusectum-7B-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/s3nh/Severusectum-7B-DPO

SGLang

How to use s3nh/Severusectum-7B-DPO 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 "s3nh/Severusectum-7B-DPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s3nh/Severusectum-7B-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "s3nh/Severusectum-7B-DPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "s3nh/Severusectum-7B-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use s3nh/Severusectum-7B-DPO with Docker Model Runner:
```
docker model run hf.co/s3nh/Severusectum-7B-DPO
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Severusectum-7B-DPO

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: FelixChao/Sectumsempra-7B-DPO
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 32]
    model: FelixChao/Sectumsempra-7B-DPO
  - layer_range: [0, 32]
    model: FelixChao/WestSeverus-7B-DPO-v2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.18
AI2 Reasoning Challenge (25-Shot)	71.50
HellaSwag (10-Shot)	88.55
MMLU (5-Shot)	64.79
TruthfulQA (0-shot)	72.45
Winogrande (5-shot)	83.27
GSM8k (5-shot)	70.51

Downloads last month: 70

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for s3nh/Severusectum-7B-DPO

FelixChao/Sectumsempra-7B-DPO

PetroGPT/WestSeverus-7B-DPO-v2

Merge model

this model

Quantizations

3 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

71.500
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

88.550
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.790
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

72.450
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

83.270
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

70.510