Downloads · 30 days
115
8% of all-time downloads
RichardErkhov/oopere_-_martra-open-gemma-2b-it-dpo-gguf
oopere_-_martra-open-gemma-2b-it-dpo-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
115
8% of all-time downloads
All-time downloads
1.4K
Public
Repo size
30.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf35.6 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
martra-open-gemma-2b-it-dpo - GGUF
language:
You can see the process with instructions for creating the model in the notebook: Aligning_DPO_gemma-2b.ipynb
To create it, we started with the google/gemma-2b-it model and applied DPO alignment using the distilabel-capybara-dpo-7k-binarized dataset.
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.
Row in the Dataset:
{'prompt': '<|user|>\nAssist me in calculating 9319357631 plus 595. Numbers and symbols only, please.<|end|>\n<|assistant|>\n', 'chosen': 'The sum of 9319357631 and 595 is 9319358226.<|end|>\n', 'rejected': 'The result of adding 9319357631 and 595 is 9319363626.<|end|>\n'}
Prompt: 3713841893836/4? Limit your response to mathematical expressions and symbols.
Response from the Base model:
To find the result of the division, we can simply divide the given number by 4: $$ \frac{3713841893836}{4} = 928460473459
Response from the fine-tuned model:
3713841893836 ÷ 4 = 928460473459
If you want to see how the model was created, you can check out the repository where the book's notebooks are kept up-to-date.