Duplicate from arcinstitute/evo2_7b

Co-authored-by: Garyk Brixi <gbrixi@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,26 @@
+---
+license: apache-2.0
+datasets:
+- arcinstitute/opengenome2
+---
+
+<img src="https://cdn-uploads.huggingface.co/production/uploads/649aee789fc303937a045f6a/IGUfG31MMvDzhdjRK-nlJ.jpeg" width="70%" />
+
+## Evo 2
+
+Evo 2 is a state-of-the-art DNA language model trained autoregressively on trillions of DNA tokens.
+
+For instructions, details, and examples, please refer to the [Evo 2 gitHub](https://github.com/ArcInstitute/evo2) and [paper](https://www.biorxiv.org/content/10.1101/2025.02.18.638918v1).
+
+Evo 2 40B and 7B checkpoints, trained up to 1 million sequence length, are available here:
+| Checkpoint name | Num layers | Num parameters |
+|------------------------------|----|----------|
+| [evo2_40b](https://huggingface.co/arcinstitute/evo2_40b) | 50 | 40B |
+| [evo2_7b](https://huggingface.co/arcinstitute/evo2_7b) | 32 | 7B  | 
+
+We also share 40B, 7B, and 1B base checkpoints trained on 8192 context length:
+| Checkpoint name | Num layers | Num parameters |
+|------------------------------|----|----------|
+| [evo2_40b_base](https://huggingface.co/arcinstitute/evo2_40b_base) | 50 | 40B |
+| [evo2_7b_base](https://huggingface.co/arcinstitute/evo2_7b_base) | 32 | 7B  | 
+| [evo2_1b_base](https://huggingface.co/arcinstitute/evo2_1b_base) | 25 | 1B  |

config.json

@@ -0,0 +1 @@
+{ "name": "Evo 2 7B", "architecture": ["StripedHyena2"], "_name_or_path": "evo2_7b.pt"}

evo2_7b.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66645929dc1b9c631f5be656da8726f38946315dc9167000a615dd626fcecf4
+size 13766621200