Note

I've forced llama.cpp to use llama-bpe tokenizer, as the checksum of the model's original tokenizer was not present in the converter code. The model has produced meaningful output in english and korean (that is what I've tried).

'Make knowledge free for everyone'

Made with

Downloads last month: 224

GGUF

Model size

7.53B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

Text Generation

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

Model tree for DevQuasar/trillionlabs.Trillion-7B-preview-GGUF

Base model

trillionlabs/Trillion-7B-preview

Quantized

(4)

this model

Collection including DevQuasar/trillionlabs.Trillion-7B-preview-GGUF

GGUFs

Collection

quantized models • 226 items • Updated 6 days ago • 2