Update README.md
Browse files
README.md
CHANGED
|
@@ -33,14 +33,14 @@ We evaluated the xTrimoPGLM (xTMLM or xTCLM) and xTrimoPGLM(100B) models on two
|
|
| 33 |
You can choose to manually download the necessary weights.
|
| 34 |
|
| 35 |
| Model |Download |
|
| 36 |
-
|
| 37 |
-
| xTrimoPGLM-1B-MLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-1b-mlm)
|
| 38 |
-
| xTrimoPGLM-3B-MLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-3b-mlm)
|
| 39 |
-
| xTrimoPGLM-10B-MLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-10b-mlm)
|
| 40 |
-
| xTrimoPGLM-1B-CLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-1b-clm)
|
| 41 |
-
| xTrimoPGLM-3B-CLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-3b-clm)
|
| 42 |
-
| xTrimoPGLM-7B-CLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-7b-clm)
|
| 43 |
-
| xTrimoPGLM-100B-Int4 (MLM or CLM) | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-100b-int4)
|
| 44 |
|
| 45 |
## How to use
|
| 46 |
### xTrimoPGLM-MLM: Masked Langeuage Models for Protein Understanding tasks
|
|
@@ -78,9 +78,6 @@ model = AutoModelForTokenClassification.from_config(config, trust_remote_code=Tr
|
|
| 78 |
|
| 79 |
```
|
| 80 |
|
| 81 |
-
|
| 82 |
-
Refer the *finetune* folder to check more finetuning examples, such as LoRA and Linear Probing.
|
| 83 |
-
|
| 84 |
### xTrimoPGLM-CLM: Casusal Langeuage Models for Protein Design
|
| 85 |
```python
|
| 86 |
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
|
|
@@ -106,9 +103,8 @@ for idx, each in enumerate(prompt):
|
|
| 106 |
output = model.chat(tokenizer, each)
|
| 107 |
print(f"\nEnd generation with length: {len(output.split())} - seqs: {output}\n")
|
| 108 |
```
|
| 109 |
-
For more inference scrpts of other models, please visit the model card of the huggingface page.
|
| 110 |
-
|
| 111 |
|
|
|
|
| 112 |
|
| 113 |
## LICENSE
|
| 114 |
|
|
|
|
| 33 |
You can choose to manually download the necessary weights.
|
| 34 |
|
| 35 |
| Model |Download |
|
| 36 |
+
|------------------|-----------------------------------------------------------------------------------------------------------|
|
| 37 |
+
| xTrimoPGLM-1B-MLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-1b-mlm) |
|
| 38 |
+
| xTrimoPGLM-3B-MLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-3b-mlm) |
|
| 39 |
+
| xTrimoPGLM-10B-MLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-10b-mlm) |
|
| 40 |
+
| xTrimoPGLM-1B-CLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-1b-clm) |
|
| 41 |
+
| xTrimoPGLM-3B-CLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-3b-clm) |
|
| 42 |
+
| xTrimoPGLM-7B-CLM | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-7b-clm) |
|
| 43 |
+
| xTrimoPGLM-100B-Int4 (MLM or CLM) | [🤗 Huggingface](https://huggingface.co/biomap-research/xtrimopglm-100b-int4)| | |
|
| 44 |
|
| 45 |
## How to use
|
| 46 |
### xTrimoPGLM-MLM: Masked Langeuage Models for Protein Understanding tasks
|
|
|
|
| 78 |
|
| 79 |
```
|
| 80 |
|
|
|
|
|
|
|
|
|
|
| 81 |
### xTrimoPGLM-CLM: Casusal Langeuage Models for Protein Design
|
| 82 |
```python
|
| 83 |
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
|
|
|
|
| 103 |
output = model.chat(tokenizer, each)
|
| 104 |
print(f"\nEnd generation with length: {len(output.split())} - seqs: {output}\n")
|
| 105 |
```
|
|
|
|
|
|
|
| 106 |
|
| 107 |
+
For more inference or fine-tuning code, datasets, and requirements, please visit our [GitHub page](https://github.com/biomap-research/xTrimoPGLM).
|
| 108 |
|
| 109 |
## LICENSE
|
| 110 |
|