34 lines
693 B
Markdown
34 lines
693 B
Markdown
|
---
|
||
|
|
tags:
|
||
|
|
- text-generation-inference
|
||
|
|
- transformers
|
||
|
|
- unsloth
|
||
|
|
- qwen3
|
||
|
|
- agent
|
||
|
|
datasets:
|
||
|
|
- NoSlop4U/opus-3-1000x
|
||
|
|
base_model:
|
||
|
|
- unsloth/Qwen3-4B-Instruct-2507
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen3 4B Instruct 2507 - Claude Opus 3 Distill
|
||
|
|
|
||
|
|
This model was trained on a non-reasoning dataset of **Claude Opus 3**.
|
||
|
|
|
||
|
|
- 🧬 Datasets:
|
||
|
|
- `NoSlop4U/opus-3-1000x`
|
||
|
|
|
||
|
|
- 🏗 Base Model:
|
||
|
|
- `unsloth/Qwen3-4B-Instruct-2507`
|
||
|
|
|
||
|
|
- ⚡ Use cases:
|
||
|
|
- Coding
|
||
|
|
- Agent
|
||
|
|
- Deep Research
|
||
|
|
|
||
|
|
- ∑ Stats (Dataset)
|
||
|
|
- Big thanks to [@NoSlop4U](https://huggingface.co/NoSlop4U) for covering this one :)
|
||
|
|
|
||
|
|
---
|
||
|
|
|
||
|
|
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|