ZraldAI v1.1

A compressed variant of Qwen3-8B.

Quality

metric this model Qwen3-8B
Wikitext-2 perplexity 10.40 9.50
MMLU-mini 100% 100%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Zrald/zraldaiv1.1")
tokenizer = AutoTokenizer.from_pretrained("Zrald/zraldaiv1.1")
Downloads last month
148
Safetensors
Model size
8B params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Zrald/zraldaiv1.1

Finetuned
Qwen/Qwen3-8B
Finetuned
(2137)
this model