Instructions to use Locutusque/OpenCerebrum-2.0-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Locutusque/OpenCerebrum-2.0-7B with Transformers:

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

pipe = pipeline("text-generation", model="Locutusque/OpenCerebrum-2.0-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Locutusque/OpenCerebrum-2.0-7B")
model = AutoModelForCausalLM.from_pretrained("Locutusque/OpenCerebrum-2.0-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Locutusque/OpenCerebrum-2.0-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Locutusque/OpenCerebrum-2.0-7B"
# 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-2.0-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Locutusque/OpenCerebrum-2.0-7B

SGLang

How to use Locutusque/OpenCerebrum-2.0-7B 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 "Locutusque/OpenCerebrum-2.0-7B" \
    --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": "Locutusque/OpenCerebrum-2.0-7B",
		"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 "Locutusque/OpenCerebrum-2.0-7B" \
        --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": "Locutusque/OpenCerebrum-2.0-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Locutusque/OpenCerebrum-2.0-7B with Docker Model Runner:
```
docker model run hf.co/Locutusque/OpenCerebrum-2.0-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenCerebrum-2.0-7B

OpenCerebrum-2.0-7B 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 with SFT and DPO on approximately 7,000 examples across 15 data sources spanning coding, math, science, multi-turn conversation, RAG, 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.

Model Details

Base Model: alpindale/Mistral-7B-v0.2-hf
Parameters: 7 billion
Fine-Tuning Dataset Size: ~7,000 examples
Fine-Tuning Data: Advanced in-house curation techniques at Cognitive Computations, with 15 different data sources for DPO and SFT.
Language: English
License: Apache 2.0

Quants

EXL2 @bartowski

https://huggingface.co/bartowski/OpenCerebrum-2.0-7B-exl2

GGUF @bartowski

https://huggingface.co/bartowski/OpenCerebrum-2.0-7B-GGUF

Intended Use

OpenCerebrum-2.0-7B 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.
As the model is based on a 7B parameter model, it has computational and memory constraints compared to larger models.

Evaluations

Tasks	Version	Filter	Metric	Value		Stderr
truthfulqa_mc2	2	none	acc	0.5182	±	0.0152
ai2_arc	N/A	none	acc	0.7060	±	0.0073
		none	acc_norm	0.7049	±	0.0074
- arc_challenge	1	none	acc	0.5000	±	0.0146
		none	acc_norm	0.5299	±	0.0146
- arc_easy	1	none	acc	0.8077	±	0.0081
		none	acc_norm	0.7912	±	0.0083
agieval_nous	N/A	none	acc	0.3778	±	0.0093
		none	acc_norm	0.3574	±	0.0093
- agieval_aqua_rat	1	none	acc	0.2402	±	0.0269
		none	acc_norm	0.2205	±	0.0261
- agieval_logiqa_en	1	none	acc	0.3164	±	0.0182
		none	acc_norm	0.3656	±	0.0189
- agieval_lsat_ar	1	none	acc	0.2130	±	0.0271
		none	acc_norm	0.1913	±	0.0260
- agieval_lsat_lr	1	none	acc	0.4078	±	0.0218
		none	acc_norm	0.3647	±	0.0213
- agieval_lsat_rc	1	none	acc	0.4981	±	0.0305
		none	acc_norm	0.4498	±	0.0304
- agieval_sat_en	1	none	acc	0.6650	±	0.0330
		none	acc_norm	0.5922	±	0.0343
- agieval_sat_en_without_passage	1	none	acc	0.4612	±	0.0348
		none	acc_norm	0.3932	±	0.0341
- agieval_sat_math	1	none	acc	0.3273	±	0.0317
		none	acc_norm	0.2818	±	0.0304

Downloads last month: 21

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Locutusque/OpenCerebrum-2.0-7B

Merges

2 models

Quantizations

4 models

Spaces using Locutusque/OpenCerebrum-2.0-7B 9

Collection including Locutusque/OpenCerebrum-2.0-7B

OpenCerebrum-2.0

Collection

My open source take on Aether Research's proprietary Cerebrum dataset. • 3 items • Updated Apr 13, 2024 • 2