Upload 4 files

README.md

@@ -1,3 +1,73 @@
----
-license: apache-2.0
----
+---
+language:
+- dna
+tags:
+- biology
+- genomics
+- foundation-model
+license: apache-2.0
+---
+
+# Evo 2 (1B Base) - Hugging Face Transformers Format
+
+This repository contains the **Evo 2 (1B Base)** model, converted to the Hugging Face Transformers format.
+
+**Original Repository:** [arcinstitute/evo2_1b_base](https://huggingface.co/arcinstitute/evo2_1b_base)  
+**Paper:** [Genome modeling and design across all domains of life with Evo 2](https://www.biorxiv.org/content/10.1101/2024.02.27.582234v1)  
+**Authors:** Garyk Brixi, Matthew G. Durrant, Jerome Ku, Michael Poli, et al.
+
+## Model Description
+
+Evo 2 is a biological foundation model trained on 9.3 trillion DNA base pairs from a curated genomic atlas spanning all domains of life. It uses the StripedHyena architecture to process long sequences (up to 1 million base pairs) at nucleotide-level resolution. This model is designed for tasks such as predicting the functional effects of mutations and generating novel genomic sequences.
+
+This version has been converted to be compatible with the `transformers` library, allowing for easy loading and inference.
+
+## Usage
+
+You can load and run this model using the `transformers` library as follows:
+
+```python
+import torch
+from transformers import Evo2ForCausalLM, Evo2Tokenizer
+
+# Replace with your local path or the Hub repo ID after uploading
+model_path = "path/to/this/repo" 
+
+print(f"Loading model from {model_path}...")
+model = Evo2ForCausalLM.from_pretrained(model_path)
+tokenizer = Evo2Tokenizer.from_pretrained(model_path)
+
+# Move to GPU if available
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device)
+
+# Input sequence (DNA)
+sequence = "ACGTACGT"
+print(f"Input: {sequence}")
+
+# Tokenize
+input_ids = tokenizer.encode(sequence, return_tensors="pt").to(device)
+
+# Generate
+print("Generating...")
+with torch.no_grad():
+    output = model.generate(input_ids, max_new_tokens=20)
+
+# Decode
+generated_sequence = tokenizer.decode(output[0])
+print(f"Output: {generated_sequence}")
+```
+
+## Citation
+
+If you use this model, please cite the original paper:
+
+```bibtex
+@article{brixi2024genome,
+  title={Genome modeling and design across all domains of life with Evo 2},
+  author={Brixi, Garyk and Durrant, Matthew G and Ku, Jerome and Poli, Michael and others},
+  journal={bioRxiv},
+  year={2024},
+  publisher={Cold Spring Harbor Laboratory}
+}
+```

config.json

@@ -0,0 +1,283 @@
+{
+  "architectures": [
+    "Evo2ForCausalLM"
+  ],
+  "attn_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1920,
+  "hyena_filter_configurations": [
+    {
+      "h_shape": [
+        128,
+        1,
+        7
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "h_shape": [
+        128,
+        1,
+        128
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "log_poles_shape": [
+        1920,
+        16,
+        1
+      ],
+      "residues_shape": [
+        1920,
+        16
+      ]
+    },
+    {},
+    {
+      "h_shape": [
+        128,
+        1,
+        7
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "h_shape": [
+        128,
+        1,
+        128
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "log_poles_shape": [
+        1920,
+        16,
+        1
+      ],
+      "residues_shape": [
+        1920,
+        16
+      ]
+    },
+    {
+      "h_shape": [
+        128,
+        1,
+        7
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "h_shape": [
+        128,
+        1,
+        128
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "log_poles_shape": [
+        1920,
+        16,
+        1
+      ],
+      "residues_shape": [
+        1920,
+        16
+      ]
+    },
+    {},
+    {
+      "h_shape": [
+        128,
+        1,
+        7
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "h_shape": [
+        128,
+        1,
+        128
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "log_poles_shape": [
+        1920,
+        16,
+        1
+      ],
+      "residues_shape": [
+        1920,
+        16
+      ]
+    },
+    {
+      "h_shape": [
+        128,
+        1,
+        7
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "h_shape": [
+        128,
+        1,
+        128
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "log_poles_shape": [
+        1920,
+        16,
+        1
+      ],
+      "residues_shape": [
+        1920,
+        16
+      ]
+    },
+    {},
+    {
+      "h_shape": [
+        128,
+        1,
+        7
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "h_shape": [
+        128,
+        1,
+        128
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "log_poles_shape": [
+        1920,
+        16,
+        1
+      ],
+      "residues_shape": [
+        1920,
+        16
+      ]
+    },
+    {
+      "h_shape": [
+        128,
+        1,
+        7
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "h_shape": [
+        128,
+        1,
+        128
+      ]
+    },
+    {
+      "D_shape": [
+        1920
+      ],
+      "log_poles_shape": [
+        1920,
+        16,
+        1
+      ],
+      "residues_shape": [
+        1920,
+        16
+      ]
+    },
+    {}
+  ],
+  "hyena_filters": 128,
+  "hyena_flip_x1x2": false,
+  "hyena_hidden_size": 1920,
+  "hyena_kernel_size": 3,
+  "hyena_order": 3,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_types": [
+    "hyena",
+    "hyena",
+    "hyena",
+    "attention",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "attention",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "attention",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "hyena",
+    "attention"
+  ],
+  "max_position_embeddings": 2048,
+  "mlp_dropout": 0.0,
+  "model_type": "evo2",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 25,
+  "num_key_value_heads": 15,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": true,
+  "vocab_size": 512
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 0,
+  "pad_token_id": 1,
+  "transformers_version": "5.0.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24757c711cc33668450ae2c81cc0207ddde947f742494301eb2fd193686fb08
+size 4431961904