Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ This model is finetuned from HuggingFaceH4/zephyr-7b-gemma-v0.1 and is finetuned
|
|
| 6 |
To improve the resoning and maths skills, we first SFT tune the gemma on Microsoft's Orca datasets.
|
| 7 |
|
| 8 |
We utilize Orca maths Hindi dataset: GenVRadmin/Aryabhatta-Orca-Maths-Hindi \
|
| 9 |
-
And original Orca maths dataset: microsoft/orca-math-word-problems-200k
|
| 10 |
|
| 11 |
This pushes the MATHS score from 24.3 in Gemma-7B to 25.5 in Zephyr-Gemma and 31.6 in GemmaOrca.
|
| 12 |
|
|
@@ -17,7 +17,7 @@ This is then finetuned on various open sourced datasets like:
|
|
| 17 |
Telugu-LLM-Labs/yahma_alpaca_cleaned_telugu_filtered_and_romanized \
|
| 18 |
Telugu-LLM-Labs/teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized \
|
| 19 |
abhinand/tamil-alpaca \
|
| 20 |
-
Tensoic/airoboros-3.2_kn \
|
| 21 |
Tensoic/gpt-teacher_kn \
|
| 22 |
Tensoic/Alpaca-Gujarati \
|
| 23 |
HydraIndicLM/bengali_alpaca_dolly_67k \
|
|
@@ -26,7 +26,7 @@ pankajmathur/alpaca_orca \
|
|
| 26 |
OdiaGenAI/Odia_Alpaca_instructions_52k \
|
| 27 |
OdiaGenAI/gpt-teacher-roleplay-odia-3k \
|
| 28 |
GenVRadmin/Samvaad-Punjabi-Mini \
|
| 29 |
-
pankajmathur/WizardLM_Orca
|
| 30 |
|
| 31 |
The model achieves following scores on benchmarks:
|
| 32 |
|
|
|
|
| 6 |
To improve the resoning and maths skills, we first SFT tune the gemma on Microsoft's Orca datasets.
|
| 7 |
|
| 8 |
We utilize Orca maths Hindi dataset: GenVRadmin/Aryabhatta-Orca-Maths-Hindi \
|
| 9 |
+
And original Orca maths dataset: microsoft/orca-math-word-problems-200k
|
| 10 |
|
| 11 |
This pushes the MATHS score from 24.3 in Gemma-7B to 25.5 in Zephyr-Gemma and 31.6 in GemmaOrca.
|
| 12 |
|
|
|
|
| 17 |
Telugu-LLM-Labs/yahma_alpaca_cleaned_telugu_filtered_and_romanized \
|
| 18 |
Telugu-LLM-Labs/teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized \
|
| 19 |
abhinand/tamil-alpaca \
|
| 20 |
+
Tensoic/airoboros-3.2_kn \
|
| 21 |
Tensoic/gpt-teacher_kn \
|
| 22 |
Tensoic/Alpaca-Gujarati \
|
| 23 |
HydraIndicLM/bengali_alpaca_dolly_67k \
|
|
|
|
| 26 |
OdiaGenAI/Odia_Alpaca_instructions_52k \
|
| 27 |
OdiaGenAI/gpt-teacher-roleplay-odia-3k \
|
| 28 |
GenVRadmin/Samvaad-Punjabi-Mini \
|
| 29 |
+
pankajmathur/WizardLM_Orca
|
| 30 |
|
| 31 |
The model achieves following scores on benchmarks:
|
| 32 |
|