Adding Evaluation Results

README.md

@@ -11,6 +11,109 @@ tags:
 datasets:
 - sarvamai/samvaad-hi-v1
 pipeline_tag: text-generation
+model-index:
+- name: Gaja-v2.00
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 51.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v2.00
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 75.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v2.00
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 40.69
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v2.00
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 41.5
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v2.00
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 71.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v2.00
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v2.00
+      name: Open LLM Leaderboard
 ---
 
 # Model 
@@ -38,3 +141,17 @@ Gaja is a Hindi/Hinglish chat model, initially trained on SarvamAI's OpenHathi m
 - Base Model: Built upon SarvamAI's OpenHathi model, Gaja inherits its foundational capabilities while being optimized for conversational tasks.
 - Fine-tuning: Gaja has undergone fine-tuning specifically for chat-based interactions, enhancing its ability to engage in meaningful conversations with users.
 - Experimental Platform: With its flexibility and adaptability, Gaja serves as a valuable platform for conducting experiments and exploring innovative approaches to chatbot development.
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_damerajee__Gaja-v2.00)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |46.98|
+|AI2 Reasoning Challenge (25-Shot)|51.79|
+|HellaSwag (10-Shot)              |75.79|
+|MMLU (5-Shot)                    |40.69|
+|TruthfulQA (0-shot)              |41.50|
+|Winogrande (5-shot)              |71.90|
+|GSM8k (5-shot)                   | 0.23|
+