Adding Evaluation Results

README.md

@@ -1,15 +1,118 @@
 ---
-license: other
 language:
 - en
-pipeline_tag: text-generation
-inference: false
+license: other
+library_name: transformers
 tags:
 - pytorch
 - llama
 - llama-2
 - qCammel-70
-library_name: transformers
+pipeline_tag: text-generation
+inference: false
+model-index:
+- name: qCammel-70x
+  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: 68.34
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augtoma/qCammel-70x
+      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: 87.87
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augtoma/qCammel-70x
+      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: 70.18
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augtoma/qCammel-70x
+      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: 57.47
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augtoma/qCammel-70x
+      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: 84.29
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augtoma/qCammel-70x
+      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: 29.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=augtoma/qCammel-70x
+      name: Open LLM Leaderboard
 ---
 # qCammel-70
 qCammel-70 is a fine-tuned version of Llama-2 70B model, trained on a distilled dataset of 15,000 instructions using QLoRA. This model is optimized for academic medical knowledge and instruction-following capabilities.
@@ -36,3 +139,17 @@ Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platf
 - [QLoRA: Efficient Finetuning of Quantized LLMs](https://arxiv.org/abs/2305.14314)
 - [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.70971)
 
+
+# [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_augtoma__qCammel-70x)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |66.31|
+|AI2 Reasoning Challenge (25-Shot)|68.34|
+|HellaSwag (10-Shot)              |87.87|
+|MMLU (5-Shot)                    |70.18|
+|TruthfulQA (0-shot)              |57.47|
+|Winogrande (5-shot)              |84.29|
+|GSM8k (5-shot)                   |29.72|
+