Downloads · 30 days
74
5% of all-time downloads
Qwen3-30B-A3B-Geminized-v0.2
Ba2han/Qwen3-30B-A3B-Geminized-v0.2
Qwen3-30B-A3B-Geminized-v0.2 is a machine learning model from Ba2han. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
[!NOTE] Use "You are an assistant with reasoning capabilities." system message to consistently trigger gemini-style thinking.
All-time downloads
1.4K
Public
Repo size
57.1 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.gguf57.1 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- May 15, 2025
- Updated
- May 22, 2025
- SHA
- c2fb4011
Base models
Model card
From the Hugging Face model README
[!NOTE] Use "You are an assistant with reasoning capabilities." system message to consistently trigger gemini-style thinking.
[!NOTE] I'm working on improving the dataset & model and will release a new, full version.
Training Dataset
- The fine-tuning dataset consists of ~450 diverse examples, 250 of which are directly from Gemini 2.5 Pro.
Trained on:
- Unsloth version of Qwen3-30B-A3B (instruct).
- 32k seq_len with examples ranging from 1k to ~20k tokens.
- Up to 2 turns of conversations.
- No benchmark data for now.
Keep in mind that it's slightly overfit since the training dataset was quite small. The model can be used to create more high quality examples for further training.
- License
- mit
- Languages
- en
- Created
- May 15, 2025
- Updated
- May 22, 2025