29 lines
1.0 KiB
Markdown
29 lines
1.0 KiB
Markdown
|
---
|
||
|
|
base_model: unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit
|
||
|
|
tags:
|
||
|
|
- text-generation-inference
|
||
|
|
- transformers
|
||
|
|
- unsloth
|
||
|
|
- qwen2
|
||
|
|
- luau
|
||
|
|
- roblox
|
||
|
|
license: apache-2.0
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen 2.5 Coder 3B (Trained with Roblox Creator Hub Docs)
|
||
|
|
This model is trained with the entire creator hub docs repo (except media)
|
||
|
|
Because i haven't export it as GGUF so sorry to devs that can't setup safetensors
|
||
|
|
(NOTE: I HAVEN'T TESTED THIS MODEL YET, I AM NOT RESPONSIBLE FOR HALLUCINATION, CODE BREAKING OR BROKEN CHAT)
|
||
|
|
(I TESTED AND IT FAILED TOO BAD. LIKE IT HALLUCINATE LOCALSCRIPT AND SERVER-TO-CLIENT STUFFS)
|
||
|
|
|
||
|
|
- **Developed by:** NoobifiedAIDept
|
||
|
|
- **Training environment:** Google Colab
|
||
|
|
- **License:** apache-2.0
|
||
|
|
- **Finetuned from model :** unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit
|
||
|
|
|
||
|
|
This qwen2 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)
|