Adding Evaluation Results

README.md

@@ -8,9 +8,112 @@ tags:
 - unsloth
 - mistral
 - trl
-base_model: alnrg2arg/blockchainlabs_7B_merged_test2_4
 datasets:
 - Open-Orca/SlimOrca
+base_model: alnrg2arg/blockchainlabs_7B_merged_test2_4
+model-index:
+- name: test3_sft_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: 61.52
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_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: 83.89
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_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: 64.79
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_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: 47.83
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_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: 81.93
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/test3_sft_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=alnrg2arg/test3_sft_4bit
+      name: Open LLM Leaderboard
 ---
 
 Benchmark Scores
@@ -45,4 +148,17 @@ Benchmark Scores
 |--------------|------:|------|-----:|------|-----:|---|-----:|
 |truthfulqa_mc2|      2|none  |     0|acc   |0.4795|±  |0.0148|
 
-Average 65.658
+Average 65.658
+# [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_alnrg2arg__test3_sft_4bit)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |56.66|
+|AI2 Reasoning Challenge (25-Shot)|61.52|
+|HellaSwag (10-Shot)              |83.89|
+|MMLU (5-Shot)                    |64.79|
+|TruthfulQA (0-shot)              |47.83|
+|Winogrande (5-shot)              |81.93|
+|GSM8k (5-shot)                   | 0.00|
+