Locutusque_-_OpenCerebrum-1.0-7b-SFT-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

OpenCerebrum-1.0-7b-SFT - GGUF

• Model creator: https://huggingface.co/Locutusque/
• Original model: https://huggingface.co/Locutusque/OpenCerebrum-1.0-7b-SFT/

Original model description:

language:

• en license: apache-2.0 tags:
• open-source
• code
• math
• chemistry
• biology
• text-generation
• question-answering datasets:
• Open-Orca/SlimOrca
• glaiveai/glaive-code-assistant
• camel-ai/physics
• camel-ai/math
• camel-ai/chemistry
• camel-ai/biology
• WizardLM/WizardLM_evol_instruct_V2_196k
• microsoft/orca-math-word-problems-200k
• grimulkan/theory-of-mind
• Vezora/Tested-22k-Python-Alpaca
• m-a-p/Code-Feedback
• Locutusque/arc-cot
• jondurbin/airoboros-2.1
• WizardLM/WizardLM_evol_instruct_70k pipeline_tag: text-generation

---

OpenCerebrum-1.0-7B-SFT

OpenCerebrum-1.0-7B-SFT 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 AetherResearch's proprietary Cerebrum model.

The model was fine-tuned on approximately 1.2 million examples across 14 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.

Model Details

• Base Model: alpindale/Mistral-7B-v0.2-hf
• Parameters: 7 billion
• Fine-Tuning Dataset Size: ~1,200,000 examples
• Fine-Tuning Data: Amalgamation of 14 public datasets
• Language: English
• License: Apache 2.0

Intended Use

OpenCerebrum-1.0-7B-SFT 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 1.2 million 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 14 datasets listed in the Datasets section, totaling approximately 1.2 million examples. Default training hyperparameters were used. In the future, the fine-tuning dataset may be condensed to more closely match the 5,000 example dataset reputedly used for the original Cerebrum model.