GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
LoNebula
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
LoNebula
Model Tree
Qwen/Qwen2.5-72B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Property | Details |
|---|---|
| Base model | Qwen2.5-72B-Instruct (72.7B parameters, Apache-2.0) |
| Method | 4-bit QLoRA (NF4 + double quant, bf16 compute) on 2 x A40, then merged to bf16 on CPU (sharded 5GB) |
| Languages | Japanese, English |
| License | Apache-2.0 (merged weights; subject to the base model license) |
| Author | LoNebula |
| Weights format | Merged bfloat16, sharded safetensors, loads directly with transformers |
PERSONA_SEED is empty by design, so the published weights carry no identity. The model is instructed to learn the user after they load it.No owner-curated identity corpus is used. A fail-closed PII scanner runs on the upload folder before publishing and aborts the upload on any hit (emails, phone-like strings, tokens, or an owner blocklist).
The released weights are a blank slate; personalization lives entirely on the user's device:
~/.my-jarvis/profile.json.~/.my-jarvis/memory.jsonl; retrieved memories are re-injected into the next prompt.export_lora_rows() converts local memory into a LoRA dataset so each user can train their own small adapter locally; it never leaves their machine.python
from my_jarvis_pipeline import load_profile, load_memory, build_messages profile = load_profile("~/.my-jarvis/profile.json")memory = load_memory("~/.my-jarvis/memory.jsonl", limit=6)messages = build_messages(profile, memory, "今日の調子はどう？")python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "LoNebula/my-jarvis-72b"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [{"role": "system", "content": "You are My-Jarvis. Learn the user's style and answer in their language."}, {"role": "user", "content": "難しいバグにぶつかったら？"}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)print(tokenizer.decode(model.generate(inputs, max_new_tokens=512)[0][inputs.shape[-1]:], skip_special_tokens=True))72B bf16 needs ~150GB of RAM/VRAM to load; use 4-bit loading (bitsandbytes) or multiple GPUs on smaller machines, or the Inference API.
Apache-2.0, subject to the base model license (Qwen2.5-72B-Instruct) and the training data licenses (Aya: Apache-2.0; izumi-lab: CC BY-SA 4.0).
from my_jarvis_pipeline import load_profile, load_memory, build_messages profile = load_profile("~/.my-jarvis/profile.json")memory = load_memory("~/.my-jarvis/memory.jsonl", limit=6)messages = build_messages(profile, memory, "今日の調子はどう？")import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "LoNebula/my-jarvis-72b"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [{"role": "system", "content": "You are My-Jarvis. Learn the user's style and answer in their language."}, {"role": "user", "content": "難しいバグにぶつかったら？"}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)print(tokenizer.decode(model.generate(inputs, max_new_tokens=512)[0][inputs.shape[-1]:], skip_special_tokens=True))