Downloads · 30 days
0
mechgraph-checkpoints
whyujjwalraj/mechgraph-checkpoints
mechgraph-checkpoints is a machine learning model from whyujjwalraj. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Pre-trained checkpoints for MechGraph: Neuro-Symbolic Molecular Mechanism Prediction.
Access
Public
Updated Nov 27, 2025
Repo size
80 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt80 MB · 100%
At a glance
- Access
- Public
- Created
- Nov 27, 2025
- Updated
- Nov 27, 2025
- SHA
- 18a73647
Model card
From the Hugging Face model README
MechGraph Checkpoints
Pre-trained checkpoints for MechGraph: Neuro-Symbolic Molecular Mechanism Prediction.
Checkpoints
| File | Description |
|---|---|
neuromatch_best.pt | NeuroMatch encoder with order embeddings for subgraph retrieval |
alignment_best.pt | Alignment stage checkpoint (graph-LLM alignment) |
Usage
import torch
from mechgraph.models.graph_encoder import GINEncoder, NeuroMatch
from mechgraph.models.projector import Graph2TokenProjector
# Load NeuroMatch
checkpoint = torch.load("checkpoints/neuromatch_best.pt", map_location="cpu")
encoder = GINEncoder(input_dim=9, hidden_dim=256, output_dim=256)
encoder.load_state_dict(checkpoint["encoder_state_dict"])
neuromatch = NeuroMatch(encoder)
neuromatch.load_state_dict(checkpoint["neuromatch_state_dict"])
Model Architecture
- GIN Encoder: 5-layer Graph Isomorphism Network
- NeuroMatch: Order embeddings for subgraph retrieval
- Graph2Token: Cross-attention projector (8 query tokens)
- LLM: Microsoft Phi-2 (2.7B parameters)
Training
Trained using three-stage pipeline:
- Stage 1 (NeuroMatch): Subgraph retrieval with max-margin loss
- Stage 2 (Alignment): Graph-LLM feature alignment
- Stage 3 (Instruction): Mechanism prediction fine-tuning
License
Apache 2.0
- Created
- Nov 27, 2025
- Updated
- Nov 27, 2025