Jiawei Zhang
commited on
Upload 5 files
Browse files- README.md +29 -3
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- metadata.json +3 -0
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
**Base model:** [westlake-repl/SaProt_650M_AF2](https://huggingface.co/westlake-repl/SaProt_650M_AF2)
|
| 6 |
+
|
| 7 |
+
**Dataset:** This dataset contains single-site and double-site mutants derived from the wild type EYFP protein. The number of samples for
|
| 8 |
+
training, validation and test is 26168, 3087 and 3088. All single-site mutants and 80% of double-site mutants for training, 10% of double-site mutants for validation and test
|
| 9 |
+
respectively. This model was trained by Jia Zheng's lab at Westlake University. The dataset will be released later by this team.
|
| 10 |
+
|
| 11 |
+
**Performance (on test set):** 0.95 Spearman's ρ
|
| 12 |
+
|
| 13 |
+
**LoRA config:**
|
| 14 |
+
- **r:** 8
|
| 15 |
+
- **lora_dropout:** 0.0
|
| 16 |
+
- **lora_alpha:** 16
|
| 17 |
+
- **target_modules:** ["query", "key", "value", "intermediate.dense", "output.dense"]
|
| 18 |
+
- **modules_to_save:** ["classifier"]
|
| 19 |
+
|
| 20 |
+
**Training config:**
|
| 21 |
+
|
| 22 |
+
- **optimizer:**
|
| 23 |
+
- **class:** AdamW
|
| 24 |
+
- **betas:** (0.9, 0.98)
|
| 25 |
+
- **weight_decay:** 0.01
|
| 26 |
+
- **learning rate:** 1e-4
|
| 27 |
+
- **epoch:** 50
|
| 28 |
+
- **batch size:** 64
|
| 29 |
+
- **precision:** 16-mixed
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "westlake-repl/SaProt_650M_AF2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": [
|
| 18 |
+
"classifier"
|
| 19 |
+
],
|
| 20 |
+
"peft_type": "LORA",
|
| 21 |
+
"r": 8,
|
| 22 |
+
"rank_pattern": {},
|
| 23 |
+
"revision": null,
|
| 24 |
+
"target_modules": [
|
| 25 |
+
"query",
|
| 26 |
+
"key",
|
| 27 |
+
"intermediate.dense",
|
| 28 |
+
"value",
|
| 29 |
+
"output.dense"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "SEQ_CLS",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:256762b088c65faccae60f7090c76db648e7ac934a97e8739a83a9167e0f3ac9
|
| 3 |
+
size 15502914
|
metadata.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"training_data_type": "AA"
|
| 3 |
+
}
|