Adding Evaluation Results

README.md

@@ -1,12 +1,114 @@
 ---
-license: llama2
-datasets:
-- Telugu-LLM-Labs/yahma_alpaca_cleaned_telugu_filtered_and_romanized
-- >-
-  Telugu-LLM-Labs/teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized
 language:
 - te
 - en
+license: llama2
+datasets:
+- Telugu-LLM-Labs/yahma_alpaca_cleaned_telugu_filtered_and_romanized
+- Telugu-LLM-Labs/teknium_GPTeacher_general_instruct_telugu_filtered_and_romanized
+model-index:
+- name: Telugu-Llama2-7B-v0-Instruct
+  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: 53.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct
+      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: 78.33
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct
+      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: 47.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct
+      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: 43.26
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct
+      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: 73.95
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct
+      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: 20.39
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct
+      name: Open LLM Leaderboard
 ---
 # Telugu-Llama2-7B-v0-Instruct
 
@@ -99,4 +201,17 @@ The model is a collaborative effort by [Ravi Theja](https://twitter.com/ravithej
 
 # Note:
 
-The model is quite sensitive to parameters and inputs and is not yet ready for production. It remains in the experimental phase, and we recommend using it accordingly.
+The model is quite sensitive to parameters and inputs and is not yet ready for production. It remains in the experimental phase, and we recommend using it accordingly.
+# [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_Telugu-LLM-Labs__Telugu-Llama2-7B-v0-Instruct)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.86|
+|AI2 Reasoning Challenge (25-Shot)|53.58|
+|HellaSwag (10-Shot)              |78.33|
+|MMLU (5-Shot)                    |47.63|
+|TruthfulQA (0-shot)              |43.26|
+|Winogrande (5-shot)              |73.95|
+|GSM8k (5-shot)                   |20.39|
+