Gemma-2-9B-it-OmniQuant-4bit – AI Model by yw223 | AlphaNeural AI

You can deploy this model and start earning money today!

yw223/
Gemma-2-9B-it-OmniQuant-4bit

like

0

text-generation

weight-only-quantization

Salesforce/wikitext

google/gemma-2-9b-it

text-generation-inference

endpoints_compatible

Views

No views yet

Gemma-2-9B-it-OmniQuant-4bit

This repository contains a W4A16 OmniQuant checkpoint derived from google/gemma-2-9b-it.

Quantization configuration

Method: OmniQuant
Weight precision: 4-bit
Activation precision: 16-bit
Group size: 128
Optimization epochs: 20
Learnable weight clipping (LWC): enabled
Learnable equivalent transformation (LET): disabled
Calibration dataset: C4 English validation split
Calibration samples: 128
Calibration sequence length: 512
Calibration seed: 42

Evaluation

Dataset	Split	Sequence length	Perplexity
WikiText2	test	2048	10.5624

The evaluation used the full tokenized WikiText2 test corpus with non-overlapping 2048-token windows.

Checkpoint format

This follows OmniQuant's fake-quantized Hugging Face save path. It is not a packed low-bit runtime checkpoint, so its storage and loading memory can remain close to FP16 despite representing W4A16 quantized weights.

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "yw223/Gemma-2-9B-it-OmniQuant-4bit"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

Transformers may report unused weight_quantizer.scales and weight_quantizer.zeros entries when loading. The fake-quantized model weights still load through the standard Transformers path used for the reported PPL.

License

Use of this checkpoint is subject to the license and terms of the base model.