Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,7 @@ SILMA.AI is a leading Generative AI startup dedicated to empowering Arabic speak
|
|
19 |
## π Our Flagship Model: SILMA 1.0 π
|
20 |
|
21 |
* **SILMA 1.0** is the **TOP-RANKED** open-weights Arabic LLM with an impressive **9 billion parameter size**, surpassing models that are over seven times larger. π
|
22 |
-
|
23 |
|
24 |
## What makes SILMA exceptional?
|
25 |
|
@@ -375,9 +375,7 @@ In creating an open model, we have carefully considered the following:
|
|
375 |
|
376 |
* Bias and Fairness
|
377 |
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
|
378 |
-
biases embedded in the training material.
|
379 |
-
scrutiny, input data pre-processing described and posterior evaluations
|
380 |
-
reported in this card.
|
381 |
* Misinformation and Misuse
|
382 |
* LLMs can be misused to generate text that is false, misleading, or harmful.
|
383 |
* Guidelines are provided for responsible use with the model, see the
|
|
|
19 |
## π Our Flagship Model: SILMA 1.0 π
|
20 |
|
21 |
* **SILMA 1.0** is the **TOP-RANKED** open-weights Arabic LLM with an impressive **9 billion parameter size**, surpassing models that are over seven times larger. π
|
22 |
+
|
23 |
|
24 |
## What makes SILMA exceptional?
|
25 |
|
|
|
375 |
|
376 |
* Bias and Fairness
|
377 |
* LLMs trained on large-scale, real-world text data can reflect socio-cultural
|
378 |
+
biases embedded in the training material.
|
|
|
|
|
379 |
* Misinformation and Misuse
|
380 |
* LLMs can be misused to generate text that is false, misleading, or harmful.
|
381 |
* Guidelines are provided for responsible use with the model, see the
|