Adding Evaluation Results

README.md

@@ -1,16 +1,119 @@
 ---
-base_model: mistralai/Mistral-7B-v0.1
-tags:
-  - mistral
-  - instruct
-  - bggpt
-  - insait
 language:
 - bg
 - en
+license: apache-2.0
 library_name: transformers
+tags:
+- mistral
+- instruct
+- bggpt
+- insait
+base_model: mistralai/Mistral-7B-v0.1
 pipeline_tag: text-generation
-license: apache-2.0
+model-index:
+- name: BgGPT-7B-Instruct-v0.2
+  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: 60.58
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.2
+      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: 82.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.2
+      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: 60.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.2
+      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: 54.63
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.2
+      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: 76.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.2
+      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: 44.12
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.2
+      name: Open LLM Leaderboard
 ---
 # INSAIT-Institute/BgGPT-7B-Instruct-v0.2
 
@@ -89,3 +192,17 @@ model = AutoModelForCausalLM.from_pretrained(
 ## Use with GGML / llama.cpp
 
 The model in GGUF format [INSAIT-Institute/BgGPT-7B-Instruct-v0.2-GGUF](https://huggingface.co/INSAIT-Institute/BgGPT-7B-Instruct-v0.2-GGUF)
+
+# [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_INSAIT-Institute__BgGPT-7B-Instruct-v0.2)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |63.08|
+|AI2 Reasoning Challenge (25-Shot)|60.58|
+|HellaSwag (10-Shot)              |82.18|
+|MMLU (5-Shot)                    |60.50|
+|TruthfulQA (0-shot)              |54.63|
+|Winogrande (5-shot)              |76.48|
+|GSM8k (5-shot)                   |44.12|
+