---
license: mit
tags: [rag, vismem, fine-tuning]
---
# VisMem RAG Fine-tuned: `gemma-3-270m-vismem-rag-0316-1016-vismem-rag-0316-2353`
## Inference
```python
import requests
from vismem_core import VisMem
from sentence_transformers import SentenceTransformer
from transformers import pipeline
# 1. Load VisMem
data = requests.get(
    "https://huggingface.co/datasets/broadfield-dev/gemma-3-270m-vismem-rag-0316-1016-vismem-kb-0316-2353/resolve/main/vismem.png",
    headers={"Authorization":"Bearer <HF_TOKEN>"}).content
mem  = VisMem.from_png_bytes(data)
emb  = SentenceTransformer('all-MiniLM-L6-v2')
# 2. RAG query
q_vec   = emb.encode([your_question])[0]
results = mem.search(q_vec, k=3)
context = "\n---\n".join(results)
# 3. Prompt
system = (
    "You are a helpful AI Assistant with visual memory.\n"
    "### RAG MEMORY (Vector Database):\n"
    "[Uploaded Doc]: None\n"
    f"[Knowledge Base]: {context}\n"
    "### EPISODIC MEMORY (Past Chat):\n"
    "[History]: None"
)
pipe = pipeline("text-generation", model="broadfield-dev/gemma-3-270m-vismem-rag-0316-1016-vismem-rag-0316-2353")
print(pipe([
    {"role":"system","content":system},
    {"role":"user","content":your_question}
], max_new_tokens=200))
```
## Config
`{
  "dataset_name": "nohurry/Opus-4.6-Reasoning-3000x-filtered",
  "rag_columns": [
    "problem",
    "thinking"
  ],
  "question_col": "problem",
  "answer_col": "solution",
  "split": "train",
  "data_config": null,
  "total_kb_docs": 2326,
  "vismem_dim": 384,
  "vismem_width": 8192,
  "vismem_height": 8192,
  "kb_repo": "broadfield-dev/gemma-3-270m-vismem-rag-0316-1016-vismem-kb-0316-2353"
}`