MetaphoricalCode
/

EVA-Gutenberg3-Qwen2.5-32B-exl3-8bpw-hb8

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

Quantized using the default exllamav3 (0.0.2) quantization process.

Original model: https://huggingface.co/nbeerbower/EVA-Gutenberg3-Qwen2.5-32B
exllamav3: https://github.com/turboderp-org/exllamav3

EVA-Gutenberg3-Qwen2.5-32B

EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2 finetuned on jondurbin/gutenberg-dpo-v0.1, nbeerbower/gutenberg2-dpo, and nbeerbower/gutenberg-moderne-dpo.

Method

ORPO tuned with 8x A100 for 2 epochs.

Downloads last month: 5

Safetensors

Model size

16.8B params

Tensor type

FP16

·

I16

·

Inference Providers NEW

Text Generation

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

Model tree for MetaphoricalCode/EVA-Gutenberg3-Qwen2.5-32B-exl3-8bpw-hb8

Base model

Qwen/Qwen2.5-32B

Finetuned

EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2

Finetuned

nbeerbower/EVA-Gutenberg3-Qwen2.5-32B

Quantized

(16)

this model

Datasets used to train MetaphoricalCode/EVA-Gutenberg3-Qwen2.5-32B-exl3-8bpw-hb8