Adding Evaluation Results

README.md

@@ -1,18 +1,113 @@
 ---
+license: other
+library_name: transformers
 tags:
 - autotrain
 - text-generation-inference
 - text-generation
 - peft
-library_name: transformers
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
-widget:
-  - messages:
-      - role: user
-        content: What is your favorite condiment?
-license: other
 datasets:
 - THUDM/LongWriter-6k
+widget:
+- messages:
+  - role: user
+    content: What is your favorite condiment?
+model-index:
+- name: autotrain-vr4a1-e5mms
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 21.42
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-vr4a1-e5mms
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 28.46
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-vr4a1-e5mms
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 12.54
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-vr4a1-e5mms
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.28
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-vr4a1-e5mms
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.04
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-vr4a1-e5mms
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 29.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=abhishek/autotrain-vr4a1-e5mms
+      name: Open LLM Leaderboard
 ---
 
 # Model Trained Using AutoTrain
@@ -45,4 +140,17 @@ response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tok
 
 # Model response: "Hello! How can I assist you today?"
 print(response)
-```
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_abhishek__autotrain-vr4a1-e5mms)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |18.40|
+|IFEval (0-Shot)    |21.42|
+|BBH (3-Shot)       |28.46|
+|MATH Lvl 5 (4-Shot)|12.54|
+|GPQA (0-shot)      | 9.28|
+|MuSR (0-shot)      | 9.04|
+|MMLU-PRO (5-shot)  |29.63|
+