Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,7 @@ pipe('भारत के प्रथम प्रधानमंत्री',
|
|
| 21 |
|
| 22 |
`sarvam-2b`'s tokenizer is built to be efficient for Indic languages and has an average fertility score of ~2 which is significantly lower than other models.
|
| 23 |
|
|
|
|
| 24 |
| |Sarvam-2B|Llama-3.1|Gemma-2|GPT-4o|
|
| 25 |
|--------|------|---------|-------|------|
|
| 26 |
|ben_Beng|2.07 |8.02 |3.72 |2.34 |
|
|
|
|
| 21 |
|
| 22 |
`sarvam-2b`'s tokenizer is built to be efficient for Indic languages and has an average fertility score of ~2 which is significantly lower than other models.
|
| 23 |
|
| 24 |
+
Here is a comparison of fertility scores between `sarvam-2b` and other popular models.
|
| 25 |
| |Sarvam-2B|Llama-3.1|Gemma-2|GPT-4o|
|
| 26 |
|--------|------|---------|-------|------|
|
| 27 |
|ben_Beng|2.07 |8.02 |3.72 |2.34 |
|