Adding Evaluation Results

README.md

@@ -7,6 +7,109 @@ base_model:
 - 01-ai/Yi-1.5-34B-Chat
 - 01-ai/Yi-1.5-34B
 pipeline_tag: text-generation
+model-index:
+- name: YiSM-34B-0rn
+  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: 69.54
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 86.67
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 78.51
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 59.68
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 83.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      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: 75.82
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=altomek/YiSM-34B-0rn
+      name: Open LLM Leaderboard
 ---
 
 #
@@ -102,3 +205,17 @@ Please remember that all YiSM-34B-0rn models operate under the apache-2.0 licens
 - [GGUF](https://huggingface.co/altomek/YiSM-34B-0rn-GGUF)
 - [8bpw](https://huggingface.co/altomek/YiSM-34B-0rn-8bpw-EXL2)
 - [measurements](https://huggingface.co/altomek/measurements/resolve/main/YiSM-34B-0rn_measurement.json) --> ExLlamav2 measurments
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_altomek__YiSM-34B-0rn)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |75.65|
+|AI2 Reasoning Challenge (25-Shot)|69.54|
+|HellaSwag (10-Shot)              |86.67|
+|MMLU (5-Shot)                    |78.51|
+|TruthfulQA (0-shot)              |59.68|
+|Winogrande (5-shot)              |83.66|
+|GSM8k (5-shot)                   |75.82|
+