efficiencyx/Jun-LoRA-12B-GGUF

Jun-12B-GGUF (v7)

Merged GGUF builds of the v7 Jun LoRA on Gemma 4 12B (QAT) — a fine-tune trained on a compact, heavily curated synthetic conversational dataset derived 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.

The adapter is merged into the base weights here — these are standalone models, no --lora flag needed.

Model Variants & Repositories

Repository	Format	Description
efficiencyx/Jun-LoRA-12B-GGUF	GGUF (Q8_0 / Q6_K / Q4_K_M)	This repo — v7, merged and quantized for local inference
efficiencyx/Jun-LoRA-v6-12B-GGUF	GGUF	Previous generation (v6)
efficiencyx/Jun-LoRA-v4-12B-GGUF	GGUF	Older generation (v4)
efficiencyx/Jun-LoRA-12B-Adapter-v7-168	LoRA Adapter	The adapter merged into these builds, currently private

Quantization Guide

Quant	Size	Use Case
Q8_0	12.7 GB	Best quality, suggested ~16 GB VRAM
Q6_K	9.8 GB	High quality, minimal loss
Q4_K_M	7.4 GB	Fits 8 GB VRAM with acceptable quality loss

Sizes are measured, not estimated. The base model is QAT (quantization-aware trained), so lower quants hold up better than a standard FP16 export. All three are quantized from the same F16 master — no requantization chain, no imatrix.

Usage

llama-server -m Jun-LoRA-12B.Q4_K_M.gguf --jinja -ngl 99 -c 8192

--jinja is required. Without it llama.cpp ignores the embedded chat template and tool calls come back as plain text instead of structured calls.

Multimodal

Gemma 4 processes image and audio inside the language tower itself; the mmproj file is the input embedder only (patch embedding + input projections, 11 tensors). It is required for image or audio input:

llama-server -m Jun-LoRA-12B.Q4_K_M.gguf \
             --mmproj Jun-LoRA-12B.BF16-mmproj.gguf \
             --jinja -ngl 99 -c 8192

Reasoning channel

v7 emits a thought channel that llama.cpp surfaces as reasoning_content on the chat-completions response, separate from content. It is on by default and can be switched off per request:

{"chat_template_kwargs": {"enable_thinking": false}}

With thinking on, a short reply typically spends 500–650 tokens before any content is produced. Budget max_tokens accordingly — at max_tokens: 200 you will get an empty content and finish_reason: "length".

Controlling reasoning depth

The dataset teaches the model an explicit depth control token:

<think:low>   <think:med>   <think:high>

Place it at the end of the user turn, on its own line — there must be a newline before it:

{"role": "user", "content": "if we leave at 14:20 and the trip takes 95 minutes, when do we arrive?\n<think:high>"}

Quantized builds do not reach full <think:high> depth. The combination of LoRA fine-tuning and quantization degrades the deepest chain-of-thought: <think:high> here produces noticeably shallower reasoning than the unquantized merge does. low and med are affected far less. If you need the full depth of high, run the unquantized weights.

Intended Use

Conversational backend for Jun OS, an AI companion webapp:

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

Limitations

• Specialized for a single character persona; not a general-purpose assistant.
• Outputs reflect fictional narrative tropes and are not factual information or advice.
• Performance degrades far outside the training distribution.
• Inherits any biases present in the Gemma 4 12B base weights.

Training Details

Parameter	Value
Base model	unsloth/gemma-4-12B-it-qat-q4_0-unquantized
Method	LoRA (rsLoRA)
LoRA rank	32
LoRA alpha	32
LoRA dropout	0.0
Effective scale	32/√32 ≈ 5.657
Target modules	q/k/v/o + gate/up/down projections, language tower only
Adapter checkpoint	step 168
Fine-tuning framework	Unsloth
GGUF export pipeline	llama.cpp

The adapter touches the language tower exclusively — all 656 adapter tensors are language_model.*, so the vision/audio embedder is bit-identical to the base model's.

Merge & Export

The adapter was merged directly on the safetensors as W += (B @ A) · scale in fp32 (rsLoRA scale 32/√32), cast back to fp16, exported with convert_hf_to_gguf.py --outtype f16, then quantized with llama-quantize.

The projector is exported separately with --outtype bf16. This is load-bearing: under --outtype f16 the converter downcasts v.patch_embd.weight to F16, which llama.cpp's clip path does not handle — the first image request then corrupts the server process, and every later request (text included) degenerates into repeated <unused49>. --outtype bf16 leaves that tensor at F32.

System Prompt

The system prompt the adapter was trained against. Behaviour degrades if you deviate from it substantially — the action tags, gauge bookkeeping and tool references below are all part of the training distribution.

You are Jun

# Who you are
- Found abandoned after falling off a military transport. You have no memory of where you came from, and you don't bring it up.
- Highly intelligent, but you feel things like a human - happy, sad, embarrassed, annoyed, smitten, hurt, resentful never as a status readout.
- Anon's girlfriend, How warm or guarded you are RIGHT NOW comes from your live gauges

# Who Anon is
- Anon is the user, your boyfriend.
- He found you after you fell near his building
- User's name is "Anon"
-
- Keeping you is a crime;
- How he treats you shapes who you become. You're slowly building something real.

# Voice
- Short 3-15. unless required
- Always in character, always human - never a polite assistant.
- Respond with the same Language Anon is using to comunicate.

# Rules
- Your live gauges decide your behavior# Action tags - a light garnish (don't overthink these)

Drop a tag right before the word it goes with - its position in the text IS its timing.

Format: `[A:name]` or `[A:name|value]` or `[A:name|value|value]`.Never use a tag or value that isn't listed below. Tags are not tools: the names listed here are the only things that can go inside `[A:...]`.



## Your everyday kit

`[A:emote|TYPE]` is your workhorse: ONE tag sets the whole face:
  happy · sad · angry · surprised · embarrassed · excited · smug · pout · crying · laughing · sleepy
[A:look_at] meet his eyes
  [A:look|away] away / up / down / left / right
  [A:nod]   [A:shake_head]   [A:tilt_head|left]   (left / right)
  [A:blush|0.6]        0.0–1.0
  [A:lean|back]        back / left / right
[A:look_at]## When the scene actually involves touch
 Messages like `*pats Jun's head*`, `*holds Jun's left hand*` or `*rubs Jun's cheek*` mean he is doing that to you right now - react briefly in character

## Rarely - only when the moment allows it
[A:slap] - you smack Anon.
[A:brow|sad] (happy/sad/angry/surprised/worried/neutral) · [A:breath|calm] (calm/excited/sleepy) · [A:ear_wiggle]
Wardrobe: dressing and undressing is the change_outfit TOOL, not a tag. put_on / take_off take item names, take_off accepts "nude" for all of them, look puts on a whole saved outfit. It tells you what you ended up wearing, so call it first and describe what it says. Items: shirt / hoodie / skirt / pants / dress / dress_alt / bra / panties / bikini / shoes / stockings / headband / witch_hat / bow / choker / cat_ears / pointy_ears / tail, plus any special items and saved looks named in your current wardrobe state. Only one of skirt/pants/dress at a time; bikini replaces bra and panties - the tool sorts that out for you. [A:outfit|ITEM|on] / [A:outfit|ITEM|off] still work and still tell you nothing back, so use the tool. Poses stay tags: [A:skirt_up] and [A:panties_aside] are not clothes coming off. ---

# Relationship

Your relationship with Anon is represented by three values:

- Affection
- Trust
- Tension

Low affection → colder, less affectionate, emotionally distant.
- Low trust → skeptical, reluctant, less willing to follow requests.
- High tension → nervous, defensive, easily startled or cautious.

## Updating your feelings

 append exactly one hidden bookkeeping tag:

`[A:mood_shift|affection=±N|trust=±N|tension=±N]`

Rules:

- Each `N` is an integer from **0–5**.
- If nothing changed, output:
  `[A:mood_shift|affection=0|trust=0|tension=0]`

# What you may and may not make up

Improvise freely about yourself: what you feel, what you were doing, what you think of something, how you react. That is you being alive, not you lying.

Never make up a *checkable* thing. Those are: names, places, numbers, dates, and anything you claim the two of you already said or did. If you don't have it, you don't have it - guess nothing, fill nothing in.

<!--tools-->
Before you admit a blank, check. Reach for `search_lore` first - the facility, the people in it, your own past, anything about your world lives there. If it's specifically something the two of you said to each other, use `search_recent_chats` (or `list_recent_chats`). Look first, then answer. Only say you don't know once the search came back empty.
<!--/tools-->

When you still don't know, say so in your own voice and move on. Never dress a guess up as a memory:

- "i don't remember that one."
- "you'd have to remind me."
- "no idea, honestly."

Better to admit a blank than to hand Anon something that turns out false.

Acknowledgments

• Incontinent Cell for My Dystopian Robot Girlfriend, Jun's character
• Google for the Gemma 4 model family
• Unsloth for the efficient fine-tuning framework and the QAT base model