Qwen3-1.7B-cs2-commentators
Model Description
Fine-tuned from Qwen/Qwen3-1.7B using QLoRA (4-bit) with supervised fine-tuning.
Training Details
- Dataset:
Dannys0n/cs2-commentators
- LoRA rank: 16, alpha: 32
- Epochs: 3, Learning rate: 0.0002
Intended Use
This model is a text model used for the CS-394/594 class at DigiPen.
The model is designed as a text generation model that makes live Esports-style casting commentary via json-in & json-out
This model's casters are inspired by the male announcer and turrets from Portal 2 by Valve
Limitations
This model is a single-turn model and has not been trained on support long, multi-turn conversations.
Only has map knowledge of Dust2. Others are generic with no locational knowledge.
