Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
datasets:
|
| 4 |
- swahili
|
| 5 |
- mc4
|
|
@@ -40,13 +40,14 @@ Fine-tuning: Utilized the LoRA approach, refining two matrices that mirror the m
|
|
| 40 |
UlizaLlama7b-1 is optimized for downstream tasks, notably those demanding instructional datasets in Swahili, English, or both. Organizations can further fine-tune it for their specific domains. Potential areas include:
|
| 41 |
1. Question-answering within specific domains.
|
| 42 |
2. Assistant-driven chat capabilities: healthcare, agriculture, legal, education, tourism and hospitality, public services, financial sectors, communication, customer assistance, commerce, etcpublic services, financial sectors, communication, customer assistance, commerce, etc.
|
|
|
|
| 43 |
Meanwhile, Jacaranda/kiswallama-pretrained offers versatility in:
|
| 44 |
-
Text Summarization
|
| 45 |
-
Autoregressive Text Completion
|
| 46 |
-
Content Generation
|
| 47 |
-
Text Rewording
|
| 48 |
-
Grammar Refinement and Editing
|
| 49 |
-
Further Research-The current UlizaLlama is available as a 7 Billion parameters model, further research can also explore availing bigger variants of UlizaLlama.
|
| 50 |
|
| 51 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 52 |
|
|
@@ -62,5 +63,4 @@ UlizaLlama7b-1 is a cutting-edge technology brimming with possibilities, yet is
|
|
| 62 |
With this in mind, the responsible course of action dictates that, prior to deploying UlizaLlama7b-1 in any applications, developers must embark on a diligent journey of safety testing and meticulous fine-tuning, customized to the unique demands of their specific use cases.
|
| 63 |
|
| 64 |
|
| 65 |
-
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 66 |
-
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
- swahili
|
| 5 |
- mc4
|
|
|
|
| 40 |
UlizaLlama7b-1 is optimized for downstream tasks, notably those demanding instructional datasets in Swahili, English, or both. Organizations can further fine-tune it for their specific domains. Potential areas include:
|
| 41 |
1. Question-answering within specific domains.
|
| 42 |
2. Assistant-driven chat capabilities: healthcare, agriculture, legal, education, tourism and hospitality, public services, financial sectors, communication, customer assistance, commerce, etcpublic services, financial sectors, communication, customer assistance, commerce, etc.
|
| 43 |
+
|
| 44 |
Meanwhile, Jacaranda/kiswallama-pretrained offers versatility in:
|
| 45 |
+
3. Text Summarization
|
| 46 |
+
4. Autoregressive Text Completion
|
| 47 |
+
5. Content Generation
|
| 48 |
+
6. Text Rewording
|
| 49 |
+
7. Grammar Refinement and Editing
|
| 50 |
+
8. Further Research-The current UlizaLlama is available as a 7 Billion parameters model, further research can also explore availing bigger variants of UlizaLlama.
|
| 51 |
|
| 52 |
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 53 |
|
|
|
|
| 63 |
With this in mind, the responsible course of action dictates that, prior to deploying UlizaLlama7b-1 in any applications, developers must embark on a diligent journey of safety testing and meticulous fine-tuning, customized to the unique demands of their specific use cases.
|
| 64 |
|
| 65 |
|
| 66 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
|
|