Update README.md
Browse files
README.md
CHANGED
@@ -23,13 +23,19 @@ including open source contract datasets.
|
|
23 |
- **License:** Apache 2.0
|
24 |
- **Finetuned from model [optional]:** BERT-based model, fine-tuning methodology described below.
|
25 |
|
26 |
-
|
27 |
|
28 |
-
|
|
|
|
|
|
|
29 |
|
30 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
31 |
|
32 |
-
|
|
|
|
|
|
|
|
|
33 |
|
34 |
### Training Procedure
|
35 |
|
|
|
23 |
- **License:** Apache 2.0
|
24 |
- **Finetuned from model [optional]:** BERT-based model, fine-tuning methodology described below.
|
25 |
|
26 |
+
## Model Use
|
27 |
|
28 |
+
from transformers import AutoTokenizer, AutoModel
|
29 |
+
|
30 |
+
tokenizer = AutoTokenizer.from_pretrained("llmware/industry-bert-contracts-v0.1")
|
31 |
+
model = AutoModel.from_pretrained("llmware/industry-bert-contracts-v0.1")
|
32 |
|
|
|
33 |
|
34 |
+
## Bias, Risks, and Limitations
|
35 |
+
|
36 |
+
This is a semantic embedding model, fine-tuned on public domain contracts and related documents. Results may vary if used outside of this
|
37 |
+
domain, and like any embedding model, there is always the potential for anomalies in the vector embedding space. No specific safeguards have
|
38 |
+
put in place for safety or mitigate potential bias in the dataset.
|
39 |
|
40 |
### Training Procedure
|
41 |
|