skmy12/Hubble-4B-v1-EXL2

EXL2 quants of TheDrummer/Hubble-4B-v1

Default parameter. 6.5bpw and 8.0 bpw uses 8 bit lm_head layer, while 4.25bpw and 5.0bpw uses 6 bit lm_head layer.

Join our Discord! https://discord.gg/Nbv9pQ88Xb

Works on Kobold 1.74!

(Layla (iOS / Android) support is in progress)

---

BeaverAI proudly presents...

Hubble 4B v1

Equipped with his five senses, man explores the universe around him and calls the adventure 'Science'.

Description

This is a finetune of Nvidia's Llama 3.1 4B Minitron - a shrunk down model of Llama 3.1 8B 128K.

Usage

• ChatML or Text Completion
• Add <|im_end|> as a stop token

Links

• Original: https://huggingface.co/TheDrummer/Hubble-4B-v1
• GGUF: https://huggingface.co/TheDrummer/Hubble-4B-v1-GGUF
• Chadquants: https://huggingface.co/bartowski/Hubble-4B-v1-GGUF

Technical Note

Hubble was trained on ChatML with <|end_of_text|> as the EOS token. If you encounter any issues with the model, please let me know!