Kukedlc
/

Qwen2-1.5B-Spanish-1.0-DPO-GGUF

Model card Files Files and versions Community

Qwen 2 1.5B SFT y DPO

SFT --> Big-Spanish 50k
DPO --> dpo-pair-spanish 0.5k

In process...

Downloads last month: 34

GGUF

Model size

1.54B params

Architecture

qwen2

Hardware compatibility

Log In to view the estimation

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Kukedlc/Qwen2-1.5B-Spanish-1.0-DPO-GGUF

Base model

Qwen/Qwen2-1.5B-Instruct

Quantized

(52)

this model

Datasets used to train Kukedlc/Qwen2-1.5B-Spanish-1.0-DPO-GGUF