BoomJules/molly-software-engineering

Molly Specialist — Software Engineering

Produces more correct implementations of common design patterns and catches concurrency bugs that the base model misses.

Part of [Molly](https://iamolly.ai/?utm_source=huggingface&utm_medium=model_card&utm_campaign=specialists&utm_content=molly-software-engineering), 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

• —Refactors legacy code into clean, testable modules with proper separation of concerns.
• —Generates correct unit tests covering edge cases and boundary conditions.
• —Identifies race conditions and deadlocks in concurrent code reviews.

Try it with

• —"How do I implement a thread-safe singleton in Java without synchronized methods?"
• —"Write a pytest fixture that provides a temporary database connection for integration tests."
• —"Refactor this 200-line function into smaller functions following the single responsibility principle."

Before you run: the base model is gated

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

1. 1.Accept the base licence: <https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct>
2. 2.Create a read token: <https://huggingface.co/settings/tokens>
3. 3.Make the token available:
4. 4.Google Colab: Secrets panel (key icon) → Add new secret → name HF_TOKEN, enable Notebook access.
5. 5.Kaggle: Add-ons → Secrets → add HF_TOKEN.
6. 6.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-software-engineering"

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-software-engineering").eval()

Adapter details

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.

Other Molly specialists

• —Quantum Software Architect
• —Quantum Communication Systems Engineer
• —Infectious Disease Physician Antimicrobial Stewardship
• —Health Informatics Medical AI Specialist
• —Clinical Trial Pharmacologist
• —Immunopharmacologist
• —Climate Analytics Manager
• —Language Technology Consultant
• —Polymer Chemist
• —Composite Materials Engineer
• —Computer Science AI
• —Computer Science Algorithms

Running several of these at once, with the routing decided for you, is what Molly does.

Licence & intended use

Adapter: CC BY-NC 4.0 (attribution, non-commercial). Base model: its own licence. Intended for research and evaluation in Software Engineering.

© 2026 Core Labs R&D.