|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- open-source |
|
- code |
|
- math |
|
- chemistry |
|
- biology |
|
- question-answering |
|
- text-generation |
|
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 |
|
--- |
|
|
|
# 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 Anthropic'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. |
