Hugging Face's logo

NewEden
/
Qwen-1.5B-Claude-F16-GGUF

GGUF
Inference Endpoints
conversational
Model card Files Community
Edit model card

GGUF F16 quant of an experimental finetune of Qwen 1.5B with Kalomaze Opus Instruct first and then Claude C2 logs. Model may produce NSFW results.

Built with Axolotl

Downloads last month
143
GGUF
Model size
1.54B params
Architecture
qwen2

16-bit

Inference API
Unable to determine this model's library. Check the docs .

Dataset used to train NewEden/Qwen-1.5B-Claude-F16-GGUF