Lunzima
/

NQLSG-Qwen2.5-14B-MegaFusion-v4-reasoning

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Uploaded model

Developed by: Lunzima
License: apache-2.0
Finetuned from model : Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v4

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 38

Safetensors

Model size

14.8B params

Tensor type

FP16

·

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported Inference Providers.

Model tree for Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v4-reasoning

Base model

Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v3

Finetuned

Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v3-alpaca_gpt4_zh

Finetuned

Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v4

Finetuned

(1)

this model

Finetunes

1 model

Quantizations

1 model

Dataset used to train Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v4-reasoning