|
---
|
|
pipeline_tag: text2text-generation
|
|
license: apache-2.0
|
|
datasets:
|
|
- ElMater06/VSCD-dataset
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# Uploaded model |
|
- **What's This?** |
|
|
|
- Vega Search Controlling Dataset or VSCD |
|
|
|
|
|
|
|
**Prompt Format: Alpaca** |
|
|
|
>### Edit this user's input to make it search for relevant keywords online. Only respond with the new string of optimized text. |
|
>### ### Instruction: {User_query} ### Response: " |
|
>### response: |
|
|
|
|
|
- VSCD-2b is a large language model trained on search queries and summarized search queries. |
|
- VSCD was trained on a synthetic dataset based off the Gemma-2b-IT model which contained 300 entries for 9 epochs, It was made to provide fast summarization of a user's query to make searching algorithms faster. |
|
- **Developed by:** ElMater06 |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** unsloth/gemma-2b-it-bnb-4bit |
|
|
|
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
