Downloads · 30 days
0
sophia-agi-lora-v1
tomyimkc/sophia-agi-lora-v1
sophia-agi-lora-v1 is a machine learning model from tomyimkc. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Wisdom before intelligence. LoRA adapter for provenance-aware instruction on Qwen/Qwen2.5-3B-Instruct.
Access
Public
Updated Jun 18, 2026
Repo size
131 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors120 MB · 88%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026
- SHA
- c006a0a1
Base models
Model card
From the Hugging Face model README
Sophia-3B (Sophia AGI LoRA adapter)
Wisdom before intelligence. LoRA adapter for provenance-aware instruction on Qwen/Qwen2.5-3B-Instruct.
- Project: github.com/tomyimkc/sophia-agi
- Dataset: tomyimkc/sophia-agi-corpus
- Version: 0.5.4
- Train split: 436 examples (benchmark cases held out)
- Benchmark total: 23 held-out cases
Load adapter
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "Qwen/Qwen2.5-3B-Instruct"
adapter = "tomyimkc/sophia-agi-lora-v1"
tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", torch_dtype="auto")
model = PeftModel.from_pretrained(model, adapter)
Usage
Train locally:
pip install -r requirements-lora.txt
python tools/prepare_lora_dataset.py
python tools/train_lora.py --4bit --epochs 3
Evaluate:
python tools/eval_local_model.py --adapter training/lora/checkpoints/sophia-v1 --with-gate
Ollama:
ollama create sophia-7b -f models/ollama/Modelfile
Always pair with runtime gate
sophia_gate_check (MCP) or agent/gate.py — weights alone do not guarantee trap safety.
- License
- mit
- Languages
- en, zh
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026