Instructions to use eren23/dpo-binarized-NeutrixOmnibe-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eren23/dpo-binarized-NeutrixOmnibe-7B with Transformers:

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

pipe = pipeline("text-generation", model="eren23/dpo-binarized-NeutrixOmnibe-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("eren23/dpo-binarized-NeutrixOmnibe-7B")
model = AutoModelForCausalLM.from_pretrained("eren23/dpo-binarized-NeutrixOmnibe-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use eren23/dpo-binarized-NeutrixOmnibe-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eren23/dpo-binarized-NeutrixOmnibe-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eren23/dpo-binarized-NeutrixOmnibe-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/eren23/dpo-binarized-NeutrixOmnibe-7B

SGLang

How to use eren23/dpo-binarized-NeutrixOmnibe-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 "eren23/dpo-binarized-NeutrixOmnibe-7B" \
    --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": "eren23/dpo-binarized-NeutrixOmnibe-7B",
		"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 "eren23/dpo-binarized-NeutrixOmnibe-7B" \
        --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": "eren23/dpo-binarized-NeutrixOmnibe-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eren23/dpo-binarized-NeutrixOmnibe-7B with Docker Model Runner:
```
docker model run hf.co/eren23/dpo-binarized-NeutrixOmnibe-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DPO Finetuned Kukedlc/NeuTrixOmniBe-7B-model-remix using argilla/OpenHermes2.5-dpo-binarized-alpha

argilla dpo binarized pairs is a dataset built on top of: https://huggingface.co/datasets/teknium/OpenHermes-2.5 using https://github.com/argilla-io/distilabel if interested.

Thx for the great data sources.

GGUF: https://huggingface.co/eren23/dpo-binarized-NeutrixOmnibe-7B-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	76.31
AI2 Reasoning Challenge (25-Shot)	72.78
HellaSwag (10-Shot)	89.05
MMLU (5-Shot)	64.60
TruthfulQA (0-shot)	76.90
Winogrande (5-shot)	85.08
GSM8k (5-shot)	69.45

Downloads last month: 70

Safetensors

Model size

7B params

Tensor type

F16

Model tree for eren23/dpo-binarized-NeutrixOmnibe-7B

Merges

11 models

Quantizations

3 models

Dataset used to train eren23/dpo-binarized-NeutrixOmnibe-7B

Spaces using eren23/dpo-binarized-NeutrixOmnibe-7B 9

Evaluation results

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

72.780
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

89.050
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.600
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

76.900
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

85.080
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

69.450