Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

Jackrong / Qwopus3.6-27B-Coder

QUANTIZED BY: UnstableLlama

Information

exl3 quantizations of Qwopus3.6-27B-Coder via exllamav3.
repo generated automatically with ezexl3.

Repo Data

REVISION	GiB	KL DIV	PPL
3.08bpw	13.10	0.0375	6.7047
4.00bpw	15.70	0.0140	6.6424
4.15bpw	16.13	0.0125	6.6411
bf16	51.75	0.0000	6.5898

CLI Download

hf download UnstableLlama/Qwopus3.6-27B-Coder-exl3 --revision "3.08bpw" --local-dir ./Qwopus3.6-27B-Coder-exl3-3.08bpw

Safetensors

Model size

9B params

Tensor type

BF16

F16

I16

Inference Providers NEW

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

Model tree for UnstableLlama/Qwopus3.6-27B-Coder-exl3-4.15bpw

Base model

Adapter

Quantized

(18)

this model