Adding Evaluation Results

README.md

@@ -1,14 +1,117 @@
 ---
-base_model: mistralai/Mistral-7B-v0.1
+language:
+- bg
+license: apache-2.0
+library_name: transformers
 tags:
 - mistral
 - instruct
 - bggpt
 - insait
-language:
-- bg
-library_name: transformers
-license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: BgGPT-7B-Instruct-v0.1
+  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: 60.24
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.1
+      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: 81.6
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.1
+      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: 59.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.1
+      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: 53.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.1
+      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: 77.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.1
+      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: 56.71
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=INSAIT-Institute/BgGPT-7B-Instruct-v0.1
+      name: Open LLM Leaderboard
 ---
 # INSAIT-Institute/BgGPT-7B-Instruct-v0.1
 
@@ -82,4 +185,17 @@ model = AutoModelForCausalLM.from_pretrained(
 
 ## Use with GGML / llama.cpp
 
-The model in GGUF format [INSAIT-Institute/BgGPT-7B-Instruct-v0.1-GGUF](https://huggingface.co/INSAIT-Institute/BgGPT-7B-Instruct-v0.1-GGUF)
+The model in GGUF format [INSAIT-Institute/BgGPT-7B-Instruct-v0.1-GGUF](https://huggingface.co/INSAIT-Institute/BgGPT-7B-Instruct-v0.1-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-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |64.82|
+|AI2 Reasoning Challenge (25-Shot)|60.24|
+|HellaSwag (10-Shot)              |81.60|
+|MMLU (5-Shot)                    |59.66|
+|TruthfulQA (0-shot)              |53.68|
+|Winogrande (5-shot)              |77.03|
+|GSM8k (5-shot)                   |56.71|
+