Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 3 |
library_name: peft
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# MISHANM/Kannada_NLP_text_generation_Llama3_8B_instruction
|
|
@@ -18,7 +20,7 @@ This model is fine-tuned for the Kannada language, capable of answering queries
|
|
| 18 |
|
| 19 |
# Training Details
|
| 20 |
|
| 21 |
-
The model is trained on approx
|
| 22 |
1. GPUs: 2*AMD Instinct™ MI210 Accelerators
|
| 23 |
|
| 24 |
|
|
|
|
| 1 |
---
|
| 2 |
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
| 3 |
library_name: peft
|
| 4 |
+
datasets:
|
| 5 |
+
- Tensoic/airoboros-3.2_kn
|
| 6 |
---
|
| 7 |
|
| 8 |
# MISHANM/Kannada_NLP_text_generation_Llama3_8B_instruction
|
|
|
|
| 20 |
|
| 21 |
# Training Details
|
| 22 |
|
| 23 |
+
The model is trained on approx 35K instruction samples.
|
| 24 |
1. GPUs: 2*AMD Instinct™ MI210 Accelerators
|
| 25 |
|
| 26 |
|