Adding Evaluation Results

README.md

@@ -1,31 +1,131 @@
 ---
 language:
 - en
+license: llama2
 library_name: transformers
-pipeline_tag: text-generation
+tags:
+- llama-2
+- code
 datasets:
 - jondurbin/airoboros-2.2
 - Open-Orca/OpenOrca
 - garage-bAInd/Open-Platypus
 - WizardLM/WizardLM_evol_instruct_V2_196k
 - TokenBender/python_eval_instruct_51k
-tags:
-- llama-2
-- code
-license: llama2
+pipeline_tag: text-generation
 model-index:
 - name: SpeechlessCoder
   results:
   - task:
       type: text-generation
     dataset:
-      type: openai_humaneval
       name: HumanEval
+      type: openai_humaneval
     metrics:
-    - name: pass@1
-      type: pass@1
+    - type: pass@1
       value: 52.439
+      name: pass@1
       verified: false
+  - 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: 41.13
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
+      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: 64.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
+      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: 38.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
+      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: 44.95
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
+      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: 63.85
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
+      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: 17.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=speechlessai/speechless-coding-7b-16k-tora
+      name: Open LLM Leaderboard
 ---
 
 <p><h1> speechless-coding-7b-16k-tora  </h1></p>
@@ -118,3 +218,17 @@ CodeLlama-34B-Instruct: 50.79
 
                                                 A100-40G x 4
 
+
+# [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_speechlessai__speechless-coding-7b-16k-tora)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |45.05|
+|AI2 Reasoning Challenge (25-Shot)|41.13|
+|HellaSwag (10-Shot)              |64.48|
+|MMLU (5-Shot)                    |38.86|
+|TruthfulQA (0-shot)              |44.95|
+|Winogrande (5-shot)              |63.85|
+|GSM8k (5-shot)                   |17.06|
+