|
|
--- |
|
|
base_model: unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- trl |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
### Contents: |
|
|
decent model (q8), surpasses iter1 and 2 (gna ignore iter3, completely useless) in terms of extracting more items from user listing, but is still prone to extracting the same item mentioned repeatedly. |
|
|
still not as good as 3b, but fast (4x faster, 69t/s in 1b and 17t/s in 3b running on 3050 laptop) and reliable enough to perform simple extraction for a listing with less than 5 items and no world name |
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** fevohh |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/Llama-3.2-1B-Instruct-unsloth-bnb-4bit |
|
|
|
|
|
This llama 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) |
|
|
|
