🧪 Experimental

Learning Rate: 2e-5

LoRA Rank: 64

LoRA Alpha: 64

Effective Batch Size: 16

Mahou-1.5-Qwen2.5-1.5B-E2

Mahou is designed to provide short messages in a conversational context. It is capable of casual conversation and character roleplay.

Chat Format

This model has been trained to use ChatML format.

<|im_start|>system
{{system}}<|im_end|>
<|im_start|>{{char}}
{{message}}<|im_end|>
<|im_start|>{{user}}
{{message}}<|im_end|>

Roleplay Format

  • Speech without quotes.
  • Actions in *asterisks*
*leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass.

SillyTavern Settings

  1. Use ChatML for the Context Template.
  2. Enable Instruct Mode.
  3. Use the Mahou ChatML Instruct preset.
  4. Use the Mahou Sampler preset.

Method

QLoRA ORPO finetuned with 2x RTX 3090 for 3 epochs.

Downloads last month
5
Safetensors
Model size
1.54B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for nbeerbower/Mahou-1.5-Qwen2.5-1.5B-E2

Dataset used to train nbeerbower/Mahou-1.5-Qwen2.5-1.5B-E2