async0x42/Rombos-Coder-V2.5-Qwen-32b-exl2_4.0bpw

Rombos-Coder-V2.5-Qwen-32b

Rombos-Coder-V2.5-Qwen-32b is a continues finetuned version of Qwen2.5-Coder-32B-Instruct. I took it upon myself to merge the instruct model with the base model myself using the Ties merge method as demonstrated in my own "Continuous Finetuning" method (Linked bellow).

https://docs.google.com/document/d/1OjbjU5AOz4Ftn9xHQrX3oFQGhQ6RDUuXQipnQ9gn6tU/edit?usp=sharing

This version of the model shows higher performance than the original instruct and base models.

Quants: (Coming soon)

GGUF:

• https://huggingface.co/bartowski/Rombos-Coder-V2.5-Qwen-32b-GGUF

• https://huggingface.co/mradermacher/Rombos-Coder-V2.5-Qwen-32b-i1-GGUF

EXL2:

Benchmarks: (Coming soon)