Update README.md
Browse files
README.md
CHANGED
@@ -7,8 +7,6 @@ license: apache-2.0
|
|
7 |
|
8 |
industry-bert-asset-management-v0.1 is part of a series of industry-fine-tuned sentence_transformer embedding models.
|
9 |
|
10 |
-
## Model Details
|
11 |
-
|
12 |
### Model Description
|
13 |
|
14 |
<!-- Provide a longer summary of what this model is. -->
|
@@ -22,18 +20,17 @@ substitute for embeddings in the asset management domain. This model was train
|
|
22 |
- **License:** Apache 2.0
|
23 |
- **Finetuned from model [optional]:** BERT-based model, fine-tuning methodology described below.
|
24 |
|
25 |
-
|
26 |
|
27 |
from transformers import AutoTokenizer, AutoModel
|
28 |
-
|
29 |
tokenizer = AutoTokenizer.from_pretrained("llmware/industry-bert-asset-management-v0.1")
|
30 |
model = AutoModel.from_pretrained("llmware/industry-bert-asset-management-v0.1")
|
31 |
|
32 |
|
33 |
## Bias, Risks, and Limitations
|
34 |
|
35 |
-
This is a semantic embedding model, fine-tuned on public domain
|
36 |
-
domain, and like any embedding model, there is always the potential for anomalies in the vector embedding space. No specific safeguards have
|
37 |
put in place for safety or mitigate potential bias in the dataset.
|
38 |
|
39 |
### Training Procedure
|
|
|
7 |
|
8 |
industry-bert-asset-management-v0.1 is part of a series of industry-fine-tuned sentence_transformer embedding models.
|
9 |
|
|
|
|
|
10 |
### Model Description
|
11 |
|
12 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
20 |
- **License:** Apache 2.0
|
21 |
- **Finetuned from model [optional]:** BERT-based model, fine-tuning methodology described below.
|
22 |
|
23 |
+
### Model Use
|
24 |
|
25 |
from transformers import AutoTokenizer, AutoModel
|
|
|
26 |
tokenizer = AutoTokenizer.from_pretrained("llmware/industry-bert-asset-management-v0.1")
|
27 |
model = AutoModel.from_pretrained("llmware/industry-bert-asset-management-v0.1")
|
28 |
|
29 |
|
30 |
## Bias, Risks, and Limitations
|
31 |
|
32 |
+
This is a semantic embedding model, fine-tuned on public domain documents regarding the business, financials and companies in the asset
|
33 |
+
management industry. Results may vary if used outside of this domain, and like any embedding model, there is always the potential for anomalies in the vector embedding space. No specific safeguards have
|
34 |
put in place for safety or mitigate potential bias in the dataset.
|
35 |
|
36 |
### Training Procedure
|