Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ pipeline_tag: text-classification
|
|
| 22 |
---
|
| 23 |
|
| 24 |
## Usage
|
| 25 |
-
Embeddings version of the base model
|
| 26 |
The 'lm_head' layer of this model has been removed, which means it can be used for embeddings. It will not perform greatly, as it needs to be further fine-tuned, as shown by [intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct).
|
| 27 |
Additionaly, in stead of a normalization layer, the hidden layers are followed up by both a classical weight and bias 1-dimensional array of 4096 values.
|
| 28 |
Further research needs to be conducted if this architecture will fully function when adding a classification head in combination with utilizing the transformers library.
|
|
|
|
| 22 |
---
|
| 23 |
|
| 24 |
## Usage
|
| 25 |
+
Embeddings version of the base model [ssmits/Falcon2-5.5B-multilingual](https://huggingface.co/ssmits/Falcon2-5.5B-multilingual/edit/main/README.md).
|
| 26 |
The 'lm_head' layer of this model has been removed, which means it can be used for embeddings. It will not perform greatly, as it needs to be further fine-tuned, as shown by [intfloat/e5-mistral-7b-instruct](https://huggingface.co/intfloat/e5-mistral-7b-instruct).
|
| 27 |
Additionaly, in stead of a normalization layer, the hidden layers are followed up by both a classical weight and bias 1-dimensional array of 4096 values.
|
| 28 |
Further research needs to be conducted if this architecture will fully function when adding a classification head in combination with utilizing the transformers library.
|