Rombos-Coder-V2.5-Qwen-14b

image/jpeg

Rombos-Coder-V2.5-Qwen-14b is a continues finetuned version of Qwen2.5-Coder-14B-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:

EXL2:

Benchmarks: (Coming soon)

Downloads last month
52
Safetensors
Model size
14.8B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for rombodawg/Rombos-Coder-V2.5-Qwen-14b

Base model

Qwen/Qwen2.5-14B
Finetuned
(17)
this model
Finetunes
1 model
Merges
2 models
Quantizations
9 models

Spaces using rombodawg/Rombos-Coder-V2.5-Qwen-14b 6

Collection including rombodawg/Rombos-Coder-V2.5-Qwen-14b