Update README.md

README.md

@@ -10,6 +10,58 @@ model-index:
   results: []
 ---
 
+Preview of dataset trained on: https://huggingface.co/datasets/manishiitg/aditi-syn-v2
+
+The synthetic dataset (https://huggingface.co/datasets/manishiitg/aditi-syn-v2) and the full data creation pipeline (https://github.com/manishiitg/aditi_dataset) have been open-sourced, enabling transparency and fostering further research in this domain. The dataset is a rich tapestry of Hinglish (a blend of Hindi and English) data, as well as a diverse array of tasks spanning tools, retrieval-augmented generation (RAG), mathematics, and reasoning – all in the Hindi language.
+
+LMJudge Eval
+============
+
+https://github.com/manishiitg/IndicLMJudge
+
+
+#### LLM Judge Language: hi 
+| Model | Language | Score | No# Questions |
+| --- | --- | --- | --- |
+| mistralai/Mixtral-8x7B-Instruct-v0.1 | hi | 8.7148 | 554 |
+| Qwen/Qwen1.5-72B-Chat-AWQ | hi | 8.3695 | 554 |
+| manishiitg/open-aditi-v6-llama3 | hi | 8.2659 | 551 |
+| Qwen/Qwen1.5-14B-Chat | hi | 8.2404 | 554 |
+| google/gemma-7b-it | hi | 7.9152 | 554 |
+| manishiitg/open-aditi-v6-gemma | hi | 7.8634 | 549 |
+| Qwen/Qwen1.5-7B-Chat | hi | 7.8587 | 554 |
+| manishiitg/open-aditi-hi-v3 | hi | 7.7644 | 554 |
+| manishiitg/open-aditi-hi-v4 | hi | 7.6150 | 554 |
+| manishiitg/open-aditi-hi-v2 | hi | 7.2518 | 554 |
+| teknium/OpenHermes-2.5-Mistral-7B | hi | 7.2489 | 554 |
+| ai4bharat/Airavata | hi | 6.9468 | 554 |
+| 01-ai/Yi-34B-Chat | hi | 6.5801 | 554 |
+| manishiitg/open-aditi-hi-v1 | hi | 4.7022 | 554 |
+| sarvamai/OpenHathi-7B-Hi-v0.1-Base | hi | 4.2834 | 598 |
+| Qwen/Qwen1.5-4B-Chat | hi | 4.1101 | 554 |
+
+
+#### LLM Judge Language: en 
+| Model | Language | Score | No# Questions |
+| --- | --- | --- | --- |
+| Qwen/Qwen1.5-14B-Chat | en | 9.1947 | 356 |
+| Qwen/Qwen1.5-72B-Chat-AWQ | en | 9.1618 | 356 |
+| Qwen/Qwen1.5-7B-Chat | en | 9.1570 | 356 |
+| 01-ai/Yi-34B-Chat | en | 9.1368 | 356 |
+| mistralai/Mixtral-8x7B-Instruct-v0.1 | en | 9.1306 | 356 |
+| manishiitg/open-aditi-v6-gemma | en | 9.1003 | 356 |
+| teknium/OpenHermes-2.5-Mistral-7B | en | 9.0230 | 356 |
+| manishiitg/open-aditi-v6-llama3 | en | 9.0197 | 356 |
+| manishiitg/open-aditi-hi-v3 | en | 8.9615 | 356 |
+| manishiitg/open-aditi-hi-v4 | en | 8.9188 | 356 |
+| google/gemma-7b-it | en | 8.8191 | 356 |
+| Qwen/Qwen1.5-4B-Chat | en | 8.7500 | 356 |
+| google/gemma-2b-it | en | 8.4671 | 356 |
+| manishiitg/open-aditi-hi-v2 | en | 8.4584 | 356 |
+| ai4bharat/Airavata | en | 7.3834 | 356 |
+| manishiitg/open-aditi-hi-v1 | en | 6.6559 | 356 |
+| sarvamai/OpenHathi-7B-Hi-v0.1-Base | en | 5.9567 | 312 |
+
 DHARMA TINY EVAL
 ============
 
@@ -27,8 +79,6 @@ DHARMA TINY EVAL
  | OpenHathi-7B-Hi-v0.1-Base |  0.2862 | 0.3333 | 0.5130 | 0.6077 | 0.4907 | 0.2301 | 0.3017 | 0.2677 | 0.1933 |
  | Airavata |  0.2751 | 0.1274 | 0.2268 | 0.0615 | 0.3866 | 0.1104 | 0.2845 | 0.1450 | 0.3383 |
  | gemma-7b-it |  0.1227 | 0.0786 | 0.0743 | 0.1808 | 0.1561 | 0.0491 | 0.1078 | 0.0818 | 0.0855 |
- | Qwen1.5-72B-Chat-AWQ |  0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
- | Qwen1.5-7B-Chat |  0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
  
  #### Language En
  
@@ -44,7 +94,7 @@ DHARMA TINY EVAL
  | open-aditi-hi-v1 |  0.8104 | 0.3902 | 0.2491 | 0.6962 | 0.5539 | 0.3681 | 0.6379 | 0.5056 | 0.5911 |
  | Airavata |  0.7026 | 0.4282 | 0.3123 | 0.7192 | 0.5651 | 0.3313 | 0.5172 | 0.3792 | 0.5093 |
  | OpenHathi-7B-Hi-v0.1-Base |  0.4684 | 0.3062 | 0.4758 | 0.6346 | 0.5167 | 0.2577 | 0.3017 | 0.2788 | 0.2714 |
- | gemma-7b-it |  0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 0.0000 |
+
  
  Task: BoolQ Metric: score