Mistral-Small-3.1-DRAFT-0.5B-GGUF

This model is meant to be used as draft model for speculative decoding with mistralai/Mistral-Small-3.1-24B-Instruct-2503 or mistralai/Mistral-Small-24B-Instruct-2501

Data info

The data are Mistral's outputs and includes all kind of tasks from various datasets in English, French, German, Spanish, Italian and Portuguese. It has been trained for 2 epochs on 20k unique examples, for a total of 12 million tokens per epoch.

Downloads last month: 546

GGUF

Model size

593M params

Architecture

qwen2

Hardware compatibility

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 alamios/Mistral-Small-3.1-DRAFT-0.5B-GGUF

Base model

Qwen/Qwen2.5-0.5B

Finetuned

alamios/Qwenstral-Small-3.1-0.5B

Finetuned

alamios/Mistral-Small-3.1-DRAFT-0.5B

Quantized

(13)

this model

Dataset used to train alamios/Mistral-Small-3.1-DRAFT-0.5B-GGUF

Collection including alamios/Mistral-Small-3.1-DRAFT-0.5B-GGUF

Draft GGUFs

Collection

5 items • Updated 22 days ago • 1