Molly Specialist — Cryptography

Correctly explains cryptographic primitives, identifies implementation pitfalls, and writes secure code using standard libraries without common errors like ECB mode or weak randomness.

Part of Molly, an orchestrator that keeps a library of small domain specialists over one quantized base and routes each request to the right one, so a single machine answers across many fields without loading a separate large model for each.

What this specialist handles well

Identifies common cryptographic implementation pitfalls like ECB mode and weak randomness
Explains elliptic curve cryptography and number theory with accurate mathematical detail
Compares post-quantum algorithms and their security tradeoffs correctly

Try it with

"Why is CBC mode with a fixed IV vulnerable, and how should I fix it?"
"Explain the difference between RSA-OAEP and RSA-PKCS1-v1.5 padding with security implications"
"How do I implement Ed25519 signing correctly in Python using the cryptography library?"

Before you run: the base model is gated

This adapter needs the base weights, and the base is access-gated. Do this once:

Accept the base licence: https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct
Create a read token: https://huggingface.co/settings/tokens
Make the token available:
- Google Colab: Secrets panel (key icon) → Add new secret → name HF_TOKEN, enable Notebook access.
- Kaggle: Add-ons → Secrets → add HF_TOKEN.
- Local: huggingface-cli login or export HF_TOKEN=...

Skipping this gives GatedRepoError / 401 Unauthorized when the base loads. A stored Colab secret is not applied automatically — authenticate in code, as below.

Quickstart

# pip install -U transformers peft accelerate
import os, torch
from huggingface_hub import login
try:
    from google.colab import userdata
    login(userdata.get("HF_TOKEN"))
except Exception:
    tok = os.environ.get("HF_TOKEN")
    login(tok) if tok else login()

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

BASE = "meta-llama/Llama-3.1-8B-Instruct"
ADAPTER = "BoomJules/molly-cryptography"

tok = AutoTokenizer.from_pretrained(BASE)
base = AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(base, ADAPTER).eval()

msgs = [{"role": "user", "content": "Your question here"}]
ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(ids, max_new_tokens=300)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

Low-VRAM (4-bit) — fits a free Colab/Kaggle GPU (~6–7 GB)

# pip install -U transformers peft accelerate bitsandbytes
import os, torch
from huggingface_hub import login
try:
    from google.colab import userdata
    login(userdata.get("HF_TOKEN"))
except Exception:
    login(os.environ.get("HF_TOKEN"))

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from peft import PeftModel

bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",
                         bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True)
tok = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct", quantization_config=bnb, device_map="auto")
model = PeftModel.from_pretrained(base, "BoomJules/molly-cryptography").eval()

Adapter details


Base model	`meta-llama/Llama-3.1-8B-Instruct`
Method	LoRA (PEFT)
Rank / alpha	32 / 64
Domain	Cryptography

Troubleshooting

GatedRepoError / 401 Unauthorized — base licence not accepted, or HF_TOKEN missing, or the Colab secret was stored but login(...) was never called.
CUDA out of memory — use the 4-bit snippet on a GPU runtime.
Adapter seems to have no effect — confirm the base id matches base_model above.