Adding Evaluation Results

README.md

@@ -1,16 +1,119 @@
 ---
+language:
+- en
+- hi
+license: llama2
 library_name: transformers
 tags:
 - hindi
 - 'english '
 - Bilingual
-license: llama2
 datasets:
 - sarvamai/samvaad-hi-v1
-language:
-- en
-- hi
 pipeline_tag: text-generation
+model-index:
+- name: Gaja-v1.00
+  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: 52.82
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v1.00
+      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: 76.31
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v1.00
+      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: 40.83
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v1.00
+      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: 44.64
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v1.00
+      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: 70.64
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v1.00
+      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: 0.91
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=damerajee/Gaja-v1.00
+      name: Open LLM Leaderboard
 ---
 # Model 
 
@@ -105,3 +208,17 @@ _ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens
 
 
 
+
+# [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-v1.00)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |47.69|
+|AI2 Reasoning Challenge (25-Shot)|52.82|
+|HellaSwag (10-Shot)              |76.31|
+|MMLU (5-Shot)                    |40.83|
+|TruthfulQA (0-shot)              |44.64|
+|Winogrande (5-shot)              |70.64|
+|GSM8k (5-shot)                   | 0.91|
+