Adding Evaluation Results

README.md

@@ -1,13 +1,116 @@
 ---
+language:
+- en
 license: apache-2.0
+library_name: transformers
 datasets:
 - Intel/orca_dpo_pairs
 - nvidia/HelpSteer
 - jondurbin/truthy-dpo-v0.1
-language:
-- en
-library_name: transformers
 pipeline_tag: text-generation
+model-index:
+- name: mistral-7B-forest-merge-v0.1
+  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: 62.8
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhishekchohan/mistral-7B-forest-merge-v0.1
+      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: 84.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhishekchohan/mistral-7B-forest-merge-v0.1
+      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: 60.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhishekchohan/mistral-7B-forest-merge-v0.1
+      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: 58.53
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhishekchohan/mistral-7B-forest-merge-v0.1
+      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: 77.19
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhishekchohan/mistral-7B-forest-merge-v0.1
+      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: 49.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhishekchohan/mistral-7B-forest-merge-v0.1
+      name: Open LLM Leaderboard
 ---
 
 ### Mistral-7B-Forest-DPO
@@ -45,4 +148,17 @@ prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_ge
 outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
 print(outputs[0]["generated_text"])
 
-```
+```
+# [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_abhishekchohan__mistral-7B-forest-merge-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |65.47|
+|AI2 Reasoning Challenge (25-Shot)|62.80|
+|HellaSwag (10-Shot)              |84.32|
+|MMLU (5-Shot)                    |60.05|
+|TruthfulQA (0-shot)              |58.53|
+|Winogrande (5-shot)              |77.19|
+|GSM8k (5-shot)                   |49.96|
+