34 lines
1.2 KiB
Markdown
34 lines
1.2 KiB
Markdown
|
---
|
||
|
|
base_model: unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
|
||
|
|
tags:
|
||
|
|
- text-generation-inference
|
||
|
|
- transformers
|
||
|
|
- unsloth
|
||
|
|
- llama
|
||
|
|
- trl
|
||
|
|
- sft
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
- hi
|
||
|
|
---
|
||
|
|
|
||
|
|
# Uploaded model
|
||
|
|
|
||
|
|
- **Developed by:** Ryder99
|
||
|
|
- **License:** apache-2.0
|
||
|
|
- **Finetuned from model :** unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
So... Since making [Llama-3.2-1B-Instruct-Hindi](https://huggingface.co/Ryder99/Llama-3.2-1B-Instruct-Hindi) I spent even more time reading the Unsloth
|
||
|
|
documentation, and with some compromises was able to finetune a 3B model (it just barely avoided OOM). This should be better than the 1B model, but I
|
||
|
|
haven't tested it out thoroughly yet. Whatever else I wrote on the 1B model card remains true, so check it out if you want. I hope you find this model useful.
|
||
|
|
|
||
|
|
For queries, or to help me train larger models ( ...I couldn't get lab access :( ... ) you can mail me [here](mailto:kanishka_chakraborty@outlook.com).
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
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)
|