Commit
•
af4024f
1
Parent(s):
27b2fdf
Update README.md
Browse files
README.md
CHANGED
@@ -53,12 +53,11 @@ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
|
|
53 |
<!-- Provide a longer summary of what this model is/does. -->
|
54 |
The model is a single shot fine tuned Instruct LLM in Hindi and dialects
|
55 |
|
56 |
-
- **Developed by:**
|
57 |
-
- **
|
58 |
-
- **Model type:** Language model
|
59 |
- **Language(s) (NLP):** hin, bho, mai, doi
|
60 |
- **License:** other
|
61 |
-
- **Parent Model:**
|
62 |
- **Resources for more information:** More information needed
|
63 |
|
64 |
|
@@ -95,7 +94,9 @@ The model is a single shot fine tuned Instruct LLM in Hindi and dialects
|
|
95 |
|
96 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
97 |
|
98 |
-
Significant research has explored bias and fairness issues with language models
|
|
|
|
|
99 |
|
100 |
|
101 |
## Recommendations
|
@@ -227,6 +228,15 @@ More information needed
|
|
227 |
# How to Get Started with the Model
|
228 |
|
229 |
Use the code below to get started with the model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
|
231 |
<details>
|
232 |
<summary> Click to expand </summary>
|
|
|
53 |
<!-- Provide a longer summary of what this model is/does. -->
|
54 |
The model is a single shot fine tuned Instruct LLM in Hindi and dialects
|
55 |
|
56 |
+
- **Developed by:** Nikhil Malhotra, Nilesh Brahme, Satish Mishra, Vinay Sharma (Makers Lab, TechMahindra)
|
57 |
+
- **Model type:** Foundational Language model
|
|
|
58 |
- **Language(s) (NLP):** hin, bho, mai, doi
|
59 |
- **License:** other
|
60 |
+
- **Parent Model:** It is the parent model on GPT architecture
|
61 |
- **Resources for more information:** More information needed
|
62 |
|
63 |
|
|
|
94 |
|
95 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
96 |
|
97 |
+
Significant research has explored bias and fairness issues with language models
|
98 |
+
(see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)).
|
99 |
+
Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
|
100 |
|
101 |
|
102 |
## Recommendations
|
|
|
228 |
# How to Get Started with the Model
|
229 |
|
230 |
Use the code below to get started with the model.
|
231 |
+
# Use a pipeline as a high-level helper
|
232 |
+
from transformers import pipeline
|
233 |
+
pipe = pipeline("text-generation", model="nickmalhotra/Indus_1.175B")
|
234 |
+
|
235 |
+
# Load model directly
|
236 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
237 |
+
|
238 |
+
tokenizer = AutoTokenizer.from_pretrained("nickmalhotra/Indus_1.175B")
|
239 |
+
model = AutoModelForCausalLM.from_pretrained("nickmalhotra/Indus_1.175B")
|
240 |
|
241 |
<details>
|
242 |
<summary> Click to expand </summary>
|