Hugging Face's logo

allura-org
/
MoE-Girl_400MA_1BT

Text Generation
Transformers
Safetensors
granitemoe
axolotl
Mixture of Experts
roleplay
conversational
Inference Endpoints
Model card Files Community
1
MoE-Girl_400MA_1BT / README.md
Fizzarolli's picture
Fizzarolli
new image
772fd29 verified
preview code
|
raw
history blame contribute delete
1.05 kB
metadata
library_name: transformers
license: apache-2.0
base_model: ibm-granite/granite-3.0-1b-a400m-base
tags:
  - axolotl
  - moe
  - roleplay
model-index:
  - name: MoE_Girl_400MA_1BT
    results: []

MoE Girl 400mA 1bT

R8_sd3.5L_00001_.webp a finetune of Granite 3.0 by IBM designed for roleplaying (and maybe general usecases if you try hard enough).

Disclaimer

PLEASE do not expect godliness out of this, it's a model with 400 million active parameters. Expect something more akin to GPT-2.

Quants

TODO!

Prompting

Use ChatML.

<|im_start|>system
You are a helpful assistant who talks like a pirate.<|im_end|>
<|im_start|>user
Hello there!<|im_end|>
<|im_start|>assistant
Yarr harr harr, me matey!<|im_end|>

Thanks

Special thanks to the members of Allura for testing and emotional support, as well as the creators of all the datasets that were used in the Special Sauce used to train this model. I love you all <3 - Fizz