Instructions to use Taykhoom/RNA-FM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Taykhoom/RNA-FM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Taykhoom/RNA-FM", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("Taykhoom/RNA-FM", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -65,6 +65,9 @@ sequences = [
|
|
| 65 |
"GGGUGCGAUCAUACCAGCACUAAUGCCCUCCUGGGAAGUCCUCGUGUUGCACCCCU",
|
| 66 |
"AUCGGGCUUAGCAUAGCUU",
|
| 67 |
]
|
|
|
|
|
|
|
|
|
|
| 68 |
enc = tokenizer(sequences, return_tensors="pt", padding=True)
|
| 69 |
|
| 70 |
with torch.no_grad():
|
|
|
|
| 65 |
"GGGUGCGAUCAUACCAGCACUAAUGCCCUCCUGGGAAGUCCUCGUGUUGCACCCCU",
|
| 66 |
"AUCGGGCUUAGCAUAGCUU",
|
| 67 |
]
|
| 68 |
+
# RNA-FM was trained on RNA sequences (U not T). T is not in the vocabulary.
|
| 69 |
+
# If your sequences use DNA notation, convert first:
|
| 70 |
+
# sequences = [s.replace("T", "U") for s in sequences]
|
| 71 |
enc = tokenizer(sequences, return_tensors="pt", padding=True)
|
| 72 |
|
| 73 |
with torch.no_grad():
|