Instructions to use Locutusque/OpenCerebrum-1.0-7b-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/OpenCerebrum-1.0-7b-DPO with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/OpenCerebrum-1.0-7b-DPO")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/OpenCerebrum-1.0-7b-DPO")
model = AutoModelForCausalLM.from_pretrained("Locutusque/OpenCerebrum-1.0-7b-DPO")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Locutusque/OpenCerebrum-1.0-7b-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/OpenCerebrum-1.0-7b-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Locutusque/OpenCerebrum-1.0-7b-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/OpenCerebrum-1.0-7b-DPO

SGLang

How to use Locutusque/OpenCerebrum-1.0-7b-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 "Locutusque/OpenCerebrum-1.0-7b-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": "Locutusque/OpenCerebrum-1.0-7b-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 "Locutusque/OpenCerebrum-1.0-7b-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": "Locutusque/OpenCerebrum-1.0-7b-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/OpenCerebrum-1.0-7b-DPO with Docker Model Runner:
```
docker model run hf.co/Locutusque/OpenCerebrum-1.0-7b-DPO
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenCerebrum-1.0-7B-DPO

OpenCerebrum-1.0-7B-DPO is an open-source language model fine-tuned from the alpindale/Mistral-7B-v0.2-hf base model on a diverse dataset aimed at replicating capabilities of Aether Research's proprietary Cerebrum model.

The model was fine-tuned on approximately 21,000 examples across 6 datasets spanning coding, math, science, reasoning, and general instruction-following. The goal was to assemble public datasets that could help the model achieve strong performance on benchmarks where Cerebrum excels.

I used the ChatML prompt format to train this model.

Model Details

Base Model: alpindale/Mistral-7B-v0.2-hf
Parameters: 7 billion
Fine-Tuning Dataset Size: ~21,000 examples
Fine-Tuning Data: Amalgamation of 6 public datasets
Language: English
License: Apache 2.0

Quants

ExLlamaV2: https://huggingface.co/bartowski/OpenCerebrum-1.0-7b-DPO-exl2
GGUF: https://huggingface.co/bartowski/OpenCerebrum-1.0-7b-DPO-GGUF
AWQ: https://huggingface.co/solidrust/OpenCerebrum-1.0-7b-DPO-AWQ

Intended Use

OpenCerebrum-1.0-7B-DPO is intended to be a powerful open-source model for coding, math, science, and general question-answering and text generation tasks. Its diverse fine-tuning data aims to equip it with broad knowledge and reasoning capabilities.

However, as an open-source replica trained on a subset of data compared to the original Cerebrum, it may not match Cerebrum's full performance. Additionally, biases and limitations of the fine-tuning data may be reflected in the model's outputs.

Limitations and Biases

The model may have biases and limitations inherited from its fine-tuning datasets. Thorough testing is needed to characterize these.
With 21,000 training examples, the fine-tuning data is still limited compared to the proprietary Cerebrum data.
As the model is based on a 7B parameter model, it has computational and memory constraints compared to larger models.

Training Details

The model was fine-tuned on the 6 datasets listed in the Datasets section, totaling approximately 21,000 examples. In the future, the fine-tuning dataset may be condensed to more closely match the ~500 example dataset reputedly used for the original Cerebrum model.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	62.78
AI2 Reasoning Challenge (25-Shot)	62.71
HellaSwag (10-Shot)	84.33
MMLU (5-Shot)	62.59
TruthfulQA (0-shot)	44.91
Winogrande (5-shot)	80.11
GSM8k (5-shot)	42.00

Downloads last month: 97

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Locutusque/OpenCerebrum-1.0-7b-DPO

Merges

3 models

Quantizations

4 models

Dataset used to train Locutusque/OpenCerebrum-1.0-7b-DPO

Spaces using Locutusque/OpenCerebrum-1.0-7b-DPO 11

Evaluation results

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

62.710
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

84.330
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

62.590
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

44.910
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

80.110
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

42.000