Feature Extraction
Transformers
Safetensors
flash_transformer
biology
genomics
long-context
custom_code
Instructions to use isyslab/DNAFlash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use isyslab/DNAFlash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="isyslab/DNAFlash", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("isyslab/DNAFlash", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from isyslab/DNAFlash: direct link, hf CLI and curl.
- Browser
- Download file 687 Bytes
-
https://huggingface.co/isyslab/DNAFlash/resolve/main/config.json
- Command line
-
hf download hf://isyslab/DNAFlash/config.json
-
curl -L -o config.json https://huggingface.co/isyslab/DNAFlash/resolve/main/config.json
687 Bytes
| { | |
| "architectures": [ | |
| "FLASHTransformerForPretrained" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "dnaflash.FLASHTransformerConfig", | |
| "AutoModel": "dnaflash.FLASHTransformerForPretrained", | |
| "AutoModelForSequenceClassification": "dnaflash.FLASHTransformerForSequenceClassification" | |
| }, | |
| "attn_dropout": 0.0, | |
| "causal": false, | |
| "expansion_factor": 2.0, | |
| "group_size": 256, | |
| "hidden_size": 1024, | |
| "laplace_attn_fn": false, | |
| "model_type": "flash_transformer", | |
| "norm_type": "scalenorm", | |
| "num_layers": 36, | |
| "query_key_dim": 128, | |
| "reduce_group_non_causal_attn": true, | |
| "shift_tokens": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.3", | |
| "vocab_size": 4096 | |
| } | |