Skip to content

pomelk1n

RuadaptQwen2.5-32B-instruct-4-bit-AWQ-Marlin

pomelk1n/RuadaptQwen2.5-32B-instruct-4-bit-AWQ-Marlin

RuadaptQwen2.5-32B-instruct-4-bit-AWQ-Marlin is a text generation model from pomelk1n. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.

Данная модель представляет собой квантизированную версию RuadaptQwen2.5-32B-instruct, выполненную с использованием метода Activation-aware Weight Quantization (AWQ) и оптимизированную с помощью ядра Marlin.

Downloads · 30 days

33

10% of all-time downloads

All-time downloads

327

Public

Parameters

32.7B

19.1 GB on disk

Likes

1

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors19.1 GB · 100%

Parameter types

How the weights are stored.

I3231.2B · 95%

Base models

Task
Text Generation
Type
qwen2
License
apache-2.0
Languages
ru
Created
Nov 19, 2024
Updated
Nov 20, 2024