Feature Extraction
Transformers
Safetensors
PyTorch
Diffusers
chemistry
foundation models
AI4Science
materials
molecules
transformer
Instructions to use ibm-research/materials.smi_ssed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-research/materials.smi_ssed with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ibm-research/materials.smi_ssed")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ibm-research/materials.smi_ssed", device_map="auto") - Diffusers
How to use ibm-research/materials.smi_ssed with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ibm-research/materials.smi_ssed", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "n_batch": 32, | |
| "n_layer": 24, | |
| "n_embd": 768, | |
| "d_state": 16, | |
| "d_conv": 4, | |
| "expand_factor": 2, | |
| "dt_rank": "auto", | |
| "dt_min": 0.001, | |
| "dt_max": 0.1, | |
| "dt_init": "random", | |
| "dt_scale": 1.0, | |
| "dt_init_floor": 0.0001, | |
| "conv_bias": 1, | |
| "bias": 0, | |
| "max_len": 202, | |
| "d_dropout": 0.1, | |
| "dropout": 0.1, | |
| "lr_start": 3e-5, | |
| "lr_multiplier": 1, | |
| "max_epochs": 500, | |
| "model_path": "../", | |
| "ckpt_filename": "smi-ssed_130.pt", | |
| "data_root": "../../moleculenet/esol", | |
| "dataset_name": "esol", | |
| "measure_name": "measured log solubility in mols per litre", | |
| "checkpoints_folder": "./checkpoints_esol", | |
| "loss_fn": "rmse", | |
| "target_metric": "rmse", | |
| "n_output": 1, | |
| "save_ckpt": 1, | |
| "start_seed": 0, | |
| "train_decoder": 1 | |
| } | |