Adding Evaluation Results

README.md

@@ -24,6 +24,109 @@ prompt_template: 'Below is an instruction that describes a task. Write a respons
 
   '
 quantized_by: TheBloke
+model-index:
+- name: medalpaca-13B-GPTQ-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: 29.35
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/medalpaca-13B-GPTQ-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: 26.32
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/medalpaca-13B-GPTQ-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: 25.44
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/medalpaca-13B-GPTQ-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: 49.51
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/medalpaca-13B-GPTQ-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: 53.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/medalpaca-13B-GPTQ-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: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/medalpaca-13B-GPTQ-4bit
+      name: Open LLM Leaderboard
 ---
 
 <!-- header start -->
@@ -330,3 +433,17 @@ The training data primarily targets the knowledge level of medical students,
 which may result in limitations when addressing the needs of board-certified physicians.
 The model has not been tested in real-world applications, so its efficacy and accuracy are currently unknown. 
 It should never be used as a substitute for a doctor's opinion and must be treated as a research tool only.
+
+# [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_TheBloke__medalpaca-13B-GPTQ-4bit)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |30.62|
+|AI2 Reasoning Challenge (25-Shot)|29.35|
+|HellaSwag (10-Shot)              |26.32|
+|MMLU (5-Shot)                    |25.44|
+|TruthfulQA (0-shot)              |49.51|
+|Winogrande (5-shot)              |53.12|
+|GSM8k (5-shot)                   | 0.00|
+