Update README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ This model is optimized for plant science by continuing pertaining on over 1.5 m
|
|
| 18 |
- **Demo [optional]:** [More Information Needed]
|
| 19 |
|
| 20 |
## How to Get Started with the Model
|
| 21 |
-
|
| 22 |
from transformers import LlamaTokenizer, LlamaForCausalLM
|
| 23 |
import torch
|
| 24 |
|
|
@@ -30,13 +30,18 @@ batch = tokenizer(instruction, return_tensors="pt", add_special_tokens=False).to
|
|
| 30 |
with torch.no_grad():
|
| 31 |
output = model.generate(**batch, max_new_tokens=512, temperature=0.7, do_sample=True)
|
| 32 |
response = tokenizer.decode(output[0], skip_special_tokens=True)
|
|
|
|
| 33 |
|
|
|
|
|
|
|
| 34 |
|
| 35 |
-
|
|
|
|
| 36 |
title={PLLaMa: An Open-source Large Language Model for Plant Science},
|
| 37 |
author={Xianjun Yang and Junfeng Gao and Wenxin Xue and Erik Alexandersson},
|
| 38 |
year={2024},
|
| 39 |
url={https://api.semanticscholar.org/CorpusID:266741610}
|
| 40 |
-
}
|
|
|
|
| 41 |
|
| 42 |
|
|
|
|
| 18 |
- **Demo [optional]:** [More Information Needed]
|
| 19 |
|
| 20 |
## How to Get Started with the Model
|
| 21 |
+
```python
|
| 22 |
from transformers import LlamaTokenizer, LlamaForCausalLM
|
| 23 |
import torch
|
| 24 |
|
|
|
|
| 30 |
with torch.no_grad():
|
| 31 |
output = model.generate(**batch, max_new_tokens=512, temperature=0.7, do_sample=True)
|
| 32 |
response = tokenizer.decode(output[0], skip_special_tokens=True)
|
| 33 |
+
```
|
| 34 |
|
| 35 |
+
## Citation
|
| 36 |
+
If you find PLLaMa useful in your research, please cite the following paper:
|
| 37 |
|
| 38 |
+
```latex
|
| 39 |
+
@inproceedings{Yang2024PLLaMaAO,
|
| 40 |
title={PLLaMa: An Open-source Large Language Model for Plant Science},
|
| 41 |
author={Xianjun Yang and Junfeng Gao and Wenxin Xue and Erik Alexandersson},
|
| 42 |
year={2024},
|
| 43 |
url={https://api.semanticscholar.org/CorpusID:266741610}
|
| 44 |
+
}
|
| 45 |
+
```
|
| 46 |
|
| 47 |
|