Adding Evaluation Results (#1)

- Adding Evaluation Results (d0c43ca501185682c0180afa9a64d11c8b9fea88)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

README.md

@@ -1,17 +1,120 @@
 ---
+language:
+- en
+license: apache-2.0
 library_name: transformers
 tags:
 - mistral
 - conversational
 - unsloth
 - chatalpaca
-license: apache-2.0
 datasets:
 - robinsmits/ChatAlpaca-20K
-language:
-- en
 inference: false
 pipeline_tag: text-generation
+model-index:
+- name: Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
+  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: 62.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
+      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: 84.55
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
+      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: 60.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
+      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: 67.29
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
+      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: 77.11
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
+      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: 40.33
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=robinsmits/Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -207,4 +310,17 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+# [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_robinsmits__Mistral-Instruct-7B-v0.2-ChatAlpacaV2-4bit)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |65.34|
+|AI2 Reasoning Challenge (25-Shot)|62.12|
+|HellaSwag (10-Shot)              |84.55|
+|MMLU (5-Shot)                    |60.66|
+|TruthfulQA (0-shot)              |67.29|
+|Winogrande (5-shot)              |77.11|
+|GSM8k (5-shot)                   |40.33|
+