Adding Evaluation Results

README.md

@@ -1,19 +1,122 @@
 ---
-base_model: LumiOpen/Poro-34B
+license: apache-2.0
 datasets:
 - cerebras/SlimPajama-627B
 - bigcode/starcoderdata
 - mc4
 - allenai/dolma
+model_name: Poro 34B
+base_model: LumiOpen/Poro-34B
 inference: false
-license: apache-2.0
 model_creator: LumiOpen
-model_name: Poro 34B
 model_type: bloom
 prompt_template: '{prompt}
 
   '
 quantized_by: TheBloke
+model-index:
+- name: Poro-34B-GPTQ
+  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: 47.01
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Poro-34B-GPTQ
+      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: 73.75
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Poro-34B-GPTQ
+      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: 32.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Poro-34B-GPTQ
+      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: 38.37
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Poro-34B-GPTQ
+      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: 71.35
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Poro-34B-GPTQ
+      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: 5.08
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TheBloke/Poro-34B-GPTQ
+      name: Open LLM Leaderboard
 ---
 <!-- markdownlint-disable MD041 -->
 
@@ -478,3 +581,17 @@ Poro is an advanced language model, primarily optimized for English, Finnish and
 ## License
 
 Poro is released under the Apache 2.0 license.
+
+# [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__Poro-34B-GPTQ)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |44.67|
+|AI2 Reasoning Challenge (25-Shot)|47.01|
+|HellaSwag (10-Shot)              |73.75|
+|MMLU (5-Shot)                    |32.47|
+|TruthfulQA (0-shot)              |38.37|
+|Winogrande (5-shot)              |71.35|
+|GSM8k (5-shot)                   | 5.08|
+