Modelpublic

efficiencyx/Jun-Lora-v2-GGUF

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

4likes113downloads

Model Card

Jun-Lora-v2

A LoRA fine-tune of Gemma 4 12B trained on syntetic multi-turn conversational data from the visual novel My Dystopian Robot Girlfriend. The model captures the personality, speech patterns, and emotional nuance of the character Jun while preserving the base model's general reasoning and instruction-following capabilities.

Model Variants & Repositories

Repository	Format	Description
`efficiencyx/Jun-Lora-v2-SAFETENSOR`	SafeTensors FP16	Full-precision merged model
`efficiencyx/Jun-Lora-v2-GGUF`	GGUF Q80 / Q6K / Q4KM	Quantized versions for local inference
`efficiencyx/Jun-Lora-v2`	LoRA Adapter	Raw adapters at checkpoints 138, 120, 90

Quantization Guide

Quant	Size (approx.)	Use Case
Q8_0	~12.8 GB	Best quality, suggested ~16 GB VRAM
Q6_K	~10.4 GB	Recommended balance of quality and performance
Q4KM	~7.6 GB	Fits on 8 GB VRAM GPUs with acceptable quality loss

Intended Use

This model is designed as the conversational backend for Jun OS, an AI companion webapp. It is intended for:

—Character-consistent multi-turn conversation in ChatML format
—AI companion / interactive fiction applications
—Research into character-faithful fine-tuning on small, high-quality datasets

Limitations

—The model is specialized for a single character persona; it is not a general-purpose assistant.
—Outputs may reflect fictional narrative tropes and should not be treated as factual information or advice.
—Performance degrades on tasks far outside the training distribution (e.g. code generation, structured data extraction).
—The model inherits any biases present in the Gemma 4 12B base weights.

Training Details

Dataset

Property	Value
Source	My Dystopian Robot Girlfriend (visual novel dialogue)
Composition	~1:1 replica of original game tone and cadence
Size	2,302 multi-turn conversations
Format	ChatML (`<	im_start	> `/` <	im_end	>`)

The dataset was constructed to preserve the character's tone, vocabulary, emotional range, and conversational patterns across a variety of in-game scenarios. Multi-turn structure ensures the model learns contextual consistency over extended exchanges.

Hyperparameters

Parameter	Value
Base model	`google/gemma-4-12b-it`
Method	LoRA
LoRA rank	64
LoRA alpha	128
Learning rate	2e-5
Batch size	8
Gradient accumulation steps	4
Effective batch size	32
Epochs	2
Total steps	138
Checkpoint interval	Every 30 steps
Optimizer	AdamW (8-bit)

Infrastructure

Component	Detail
Training GPU	NVIDIA A100 80GB SXM4
Fine-tuning framework	Unsloth
GGUF export pipeline	llama.cpp

Evaluation

Quantitative

Metric	Value
Final training loss	~1.21
Final eval loss	~1.24

The narrow gap between training and eval loss indicates the model generalizes well without significant overfitting, despite the relatively small dataset size.

Qualitative

—Character consistency: The model maintains Jun's personality, speech patterns, and emotional responses across varied conversational contexts.
—Reasoning preservation: General reasoning capabilities from the Gemma 4 12B base remain intact; the model can engage in logical discussion while staying in character.
—Generalization: The model handles novel conversational scenarios not present in the training set while preserving character-faithful responses.

Checkpoint Selection

Multiple adapter checkpoints are provided (steps 90, 120, 138) to allow users to select the best trade-off between character adherence and generalization for their use case. Earlier checkpoints may exhibit slightly more creative freedom, while the final checkpoint (138) has the strongest character lock-in.

Acknowledgments

—Incontinent Cell for *My Dystopian Robot Girlfriend*, Jun's character
—Google for the Gemma 4 model family
—Google Colaboratory for allowing easy and cheap access to powerful GPU
—Unsloth for the efficient fine-tuning framework