πŸ§ͺ MegaSciMoE‑1.2B

A lightweight open MoE language model focused on science reasoning and instruction-following tasks. Fine-tuned using Unsloth on top of LiquidAI’s LFM2‑1.2B architecture.


πŸ”¬ Model Overview

  • Model Type: Sparse Mixture-of-Experts (MoE)
  • Base: LiquidAI LFM2‑1.2B
  • Fine-tuned with: Unsloth LoRA
  • Focus Areas: Physics, Chemistry, Biology, Scientific QA
  • Parameter Efficiency: Only 2 experts active (~250M active params)
  • Design Goal: Run efficiently on consumer GPUs and edge devices

🧠 Capabilities

  • Respond to structured science-related instructions
  • Generate concise, factual explanations in STEM topics
  • Follow multiturn question-answer patterns
  • Summarize technical descriptions in plain language

πŸš€ Example Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained("yasserrmd/MegaSciMoE-1.2B", torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained("yasserrmd/MegaSciMoE-1.2B")

prompt = "What is the difference between an ionic and covalent bond?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

πŸ“š Training Data

MegaSciMoE-1.2B was fine-tuned on a blend of:

  • Multiturn scientific dialogues
  • Instruction-based question answering
  • Simulated domain-specific prompts in physics, chemistry, and biology
  • Scientific corpus extracted from open datasets

πŸ“Ž Sample Prompts

Q: What is a neutron made of?
A: A neutron is composed of three quarks (two down quarks and one up quark)...

---

Q: Define osmosis in simple terms.
A: Osmosis is the movement of water across a membrane...

---

Q: What is the role of mitochondria?
A: Mitochondria are the powerhouses of the cell...

πŸ§ͺ Benchmark Intent

Planned evaluations on:

  • ARC-Challenge
  • PubMedQA
  • ScienceQA (Note: No math-based datasets included in this build)

βš™οΈ Technical Details

  • LoRA fine-tuning with Unsloth on 1.2B MoE model
  • Memory-efficient inference (fits on T4, L4, RTX 3060, even CPU)
  • GGUF and FP16 variants to be released

πŸ“„ License

Apache 2.0 β€” free to use and modify with attribution. Ensure upstream license compatibility before commercial use.


🀝 Acknowledgements

  • Thanks to Unsloth, LiquidAI, and Hugging Face for enabling this build
  • Visuals rendered with scientific prompts and surreal-futuristic style

Downloads last month
7
Safetensors
Model size
1.17B params
Tensor type
BF16
Β·
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for yasserrmd/MegaSciMoE-1.2B

Base model

LiquidAI/LFM2-1.2B
Finetuned
(12)
this model
Quantizations
1 model

Dataset used to train yasserrmd/MegaSciMoE-1.2B