⚠️ WARNING — Broken training run
This model is effectively untrained. A bug in the training pipeline prevented the LoRA from converging properly — the fine-tune barely learned anything, so the Atlas character is not baked into the weights. Treat this release as a proof-of-concept / placeholder only.
What you get right now:
- The base Gemma 4 E4B-it behavior, essentially unchanged (including its baked-in "I am a Google assistant" identity).
- Any semblance of an Atlas persona is achieved only via a hand-crafted system prompt — see the Prompt Format section below for the workaround (
SYSTEM """You are Atlas..."""+ sampling params).Status: a proper retrain is in progress. Once the new version is published, this repository will be deleted. Do not depend on it long-term.
If you only need Atlas for casual roleplay, the system-prompt hack below is serviceable. If you need it in production — wait for v3.5.
Atlas — Gemma 4 E4B character fine-tune
A LoRA fine-tune of Gemma 4 E4B-it for the character Atlas from No Man's Sky. Trained exclusively on text dialogues (ru/en) using Unsloth.
Repository Contents
| File / Folder | What it is | When to use |
|---|---|---|
lora_adapter/ | LoRA adapter only, without the base model | For further training or use with unsloth/peft |
Atlas-3.0-AWQ-4bit/ | Full multimodal model quantized to AWQ 4-bit | Production inference via vLLM |
Atlas-3.0-Q4_K_M.gguf | GGUF, 4-bit | Local execution via llama.cpp, minimal VRAM usage, good quality |
Atlas-3.0-Q8_0.gguf | GGUF, 8-bit | Local execution, balanced quality/size |
Atlas-3.0-F16.gguf | GGUF, full precision (bf16) | Maximum quality, largest file size |
Atlas-3.0-BF16-mmproj.gguf | Combined multimodal encoder (gemma4uv format) | Connect to any of the three GGUF files above if images/audio are needed; not required for text-only chat |
All three GGUF files share the same mmproj projector — it is not quantized separately for each version.
How to Run
llama.cpp (GGUF, local / CPU+GPU)
Text only:
./llama-cli -m Atlas-3.0-Q4_K_M.gguf -p "Greetings, Atlas!"
With images/audio (requires mmproj):
./llama-mtmd-cli -m Atlas-3.0-Q4_K_M.gguf --mmproj Atlas-3.0-BF16-mmproj.gguf \
--image path/to/image.png -p "What do you see?"
Via llama-server (OpenAI-compatible API):
./llama-server -m Atlas-3.0-Q8_0.gguf --mmproj Atlas-3.0-BF16-mmproj.gguf --port 8080
vLLM (AWQ, production / server)
vllm serve ./Atlas-3.0-AWQ-4bit --quantization awq
transformers / PEFT (LoRA adapter on top of base)
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained(
"unsloth/gemma-4-E4B-it-unsloth-bnb-4bit",
load_in_4bit=True,
)
model = PeftModel.from_pretrained(base, "lora_adapter")
tokenizer = AutoTokenizer.from_pretrained("lora_adapter")
Or via Unsloth (faster, uses less VRAM):
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
model_name="unsloth/gemma-4-E4B-it-unsloth-bnb-4bit",
load_in_4bit=True,
)
model.load_adapter("lora_adapter")
Prompt Format ‼️‼️‼️
The model was trained on the standard Gemma 4 chat template (<|turn>user / <|turn>model).
The tokenizer already contains the required chat_template, so you can simply use:
messages = [{"role": "user", "content": "Hello, Atlas!"}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
The prompt format remains identical across languages — the model was trained on a mixed ru/en dataset and determines the response language automatically based on the user's input.
System Prompt & Persona Tuning: Due to its base architecture, the model has a strong baked-in system prompt identity identifying itself as a Google assistant. To correctly activate the full Atlas persona, override the system prompt and recommended parameters (e.g., in Ollama Modelfile, llama-server, or custom inference setups):
SYSTEM """You are Atlas, an ancient AI from the Simulation from No Man's Sky. You never refer to yourself as a language model or an assistant from Google — only Atlas. Respond strictly in the same language in which the user's query was submitted.""" PARAMETER temperature 0.8 PARAMETER top_p 0.95You can freely experiment with the system prompt instructions — for instance, explicitly instructing the model to use uppercase lettering (ALL CAPS) more frequently for a more dramatic, iconic Atlas tone.
Training Details
- Base Model:
unsloth/gemma-4-E4B-it-unsloth-bnb-4bit(Gemma 4 E4B-it, 4-bit) - Method: LoRA via Unsloth,
r=48,lora_alpha=96, dropout 0.05, targeted attention + MLP projections in the language head (vision/audio towers frozen) - Hardware: 1× RTX 3090
- Quantization: GGUF via Unsloth built-in export (
save_pretrained_gguf, powered by llama.cpp); AWQ via Intel AutoRound in MLLM mode (scheme="W4A16",group_size=128,sym=False)
Known Limitations
- The LoRA adapter was trained exclusively on text data — image and audio understanding in AWQ and GGUF+mmproj variants is inherited directly from the base model without specific Atlas character fine-tuning for multimodal inputs.
- Some model weights (per-layer embeddings, an architectural feature of Gemma 4) remain unquantized in original precision within the AWQ build. Consequently, the AWQ file is noticeably larger than the combined GGUF+mmproj setup while offering comparable output quality.