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
Upload config.json
Browse files- config.json +34 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"n_batch": 32,
|
| 3 |
+
"n_layer": 24,
|
| 4 |
+
"n_embd": 768,
|
| 5 |
+
"d_state": 16,
|
| 6 |
+
"d_conv": 4,
|
| 7 |
+
"expand_factor": 2,
|
| 8 |
+
"dt_rank": "auto",
|
| 9 |
+
"dt_min": 0.001,
|
| 10 |
+
"dt_max": 0.1,
|
| 11 |
+
"dt_init": "random",
|
| 12 |
+
"dt_scale": 1.0,
|
| 13 |
+
"dt_init_floor": 0.0001,
|
| 14 |
+
"conv_bias": 1,
|
| 15 |
+
"bias": 0,
|
| 16 |
+
"max_len": 202,
|
| 17 |
+
"d_dropout": 0.1,
|
| 18 |
+
"dropout": 0.1,
|
| 19 |
+
"lr_start": 3e-5,
|
| 20 |
+
"lr_multiplier": 1,
|
| 21 |
+
"max_epochs": 500,
|
| 22 |
+
"model_path": "../",
|
| 23 |
+
"ckpt_filename": "smi-ssed_130.pt",
|
| 24 |
+
"data_root": "../../moleculenet/esol",
|
| 25 |
+
"dataset_name": "esol",
|
| 26 |
+
"measure_name": "measured log solubility in mols per litre",
|
| 27 |
+
"checkpoints_folder": "./checkpoints_esol",
|
| 28 |
+
"loss_fn": "rmse",
|
| 29 |
+
"target_metric": "rmse",
|
| 30 |
+
"n_output": 1,
|
| 31 |
+
"save_ckpt": 1,
|
| 32 |
+
"start_seed": 0,
|
| 33 |
+
"train_decoder": 1
|
| 34 |
+
}
|