rubenroy/Geneva-12B-GCv2-1m

Geneva 12B GammaCorpus v2-1m

A Mistral NeMo model fine-tuned on the GammaCorpus dataset

Overview

Geneva 12B GammaCorpus v2-1m is a fine-tune of Mistral's Mistral Nemo Instruct 2407 model. Geneva is designed to outperform other models that have a similar size while also showcasing GammaCorpus v2-1m.

Model Details

• Base Model: mistralai/Mistral-Nemo-Instruct-2407
• Parameters: 12B
• Layers: 40
• Dim: 5,120
• Head dim: 128
• Hidden dim: 14,336
• Activation Function: SwiGLU
• Number of heads: 32
• Number of kv-heads: 8 (GQA)
• Vocabulary size: 2**17 ~= 128k
• Rotary embeddings (theta = 1M)

Training Details

Geneva-12B-GCv2-1m underwent fine-tuning with 1 A100 GPU for ~40 minutes and trained with the Unsloth framework. Geneva-12B-GCv2-1m was trained for 60 Epochs.

Usage

Requirements

Please use the following Transformers version here:

pip install git+https://github.com/huggingface/transformers.git

Quickstart

If you want to use Hugging Face transformers to generate text, you can do something like this:

from transformers import pipeline

prompt = "How tall is the Eiffel tower?"

messages = [
    {"role": "system", "content": "You are a helpful assistant named Geneva, built on the Mistral NeMo model developed by Mistral AI, and fine-tuned by Ruben Roy."},
    {"role": "user", "content": prompt},
]

infer = pipeline("text-generation", model="rubenroy/Geneva-12B-GCv2-1m", max_new_tokens=128)

infer(messages)

About GammaCorpus

This model, and all Geneva models, are trained with GammaCorpus. GammaCorpus is a dataset on HuggingFace that is filled with structured and filtered multi-turn conversations. GammaCorpus has 4 version with different sizes in each. These are the following versions and sizes:

GammaCorpus v1

• 10k UNFILTERED
• 50k UNFILTERED
• 70k UNFILTERED

Here is a link to the GCv1 dataset collection:
https://huggingface.co/collections/rubenroy/gammacorpus-v1-67935e4e52a04215f15a7a60

GammaCorpus v2

• 10k
• 50k
• 100k
• 500k
• 1m <-- This is the version of GammaCorpus v2 that the Geneva model you are using was trained on.
• 5m

Here is a link to the GCv2 dataset collection:
https://huggingface.co/collections/rubenroy/gammacorpus-v2-67935e895e1259c404a579df

GammaCorpus CoT

• Math 170k

Here is a link to the GC-CoT dataset collection:
https://huggingface.co/collections/rubenroy/gammacorpus-cot-6795bbc950b62b1ced41d14f

GammaCorpus QA

• Fact 450k

Here is a link to the GC-QA dataset collection:
https://huggingface.co/collections/rubenroy/gammacorpus-qa-679857017bb3855234c1d8c7

The link to the full GammaCorpus dataset collection can be found here.

Known Limitations:

• Bias: We have tried our best to mitigate as much bias we can, but please be aware of the possibility that the model might generate some biased answers.

Licence:

The model is released under the Apache 2.0 License. Please refer to the license for usage rights and restrictions.