Adding Evaluation Results (#1)

- Adding Evaluation Results (d4540048eab11a55d6e3381ed8d41d34277bd896)


Co-authored-by: Open LLM Leaderboard PR Bot <[email protected]>

README.md

@@ -1,83 +1,194 @@
 ---
-library_name: transformers
-license: mit
 language:
 - en
 - vi
-pipeline_tag: text-generation
-base_model: HuggingFaceH4/zephyr-7b-beta
+license: mit
+library_name: transformers
 tags:
 - ghost
-model-index:
-  - name: lamhieu/ghost-7b-v0.9.0
-    results:
-    - task:
-        type: text-generation
-      dataset:
-        type: vmlu_v1.5
-        name: VMLU
-      metrics:
-        - name: Average
-          type: avg
-          value: 36.06
-          verified: true
-        - name: STEM
-          type: stem
-          value: 33.54
-          verified: true
-        - name: Social science
-          type: ss
-          value: 38.74
-          verified: true
-        - name: Humanities
-          type: hm
-          value: 37.15
-          verified: true
-        - name: Other
-          type: ot
-          value: 36.78
-          verified: true
-    - task:
-        type: text-generation
-      dataset:
-        type: open_llm_leaderboard
-        name: Open LLM Leaderboard
-      source:
-        name: Open LLM Leaderboard
-        url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
-      metrics:
-        - name: Average
-          type: avg
-          value: 56.89
-          verified: true
-        - name: ARC
-          type: arc
-          value: 53.07
-          verified: true
-        - name: HellaSwag
-          type: hs
-          value: 77.93
-          verified: true
-        - name: HellaSwag
-          type: hs
-          value: 77.93
-          verified: true
-        - name: MMLU
-          type: mmlu
-          value: 55.09
-          verified: true
-        - name: Winogrande
-          type: wg
-          value: 73.72
-          verified: true
-        - name: GSM8K
-          type: gsm8k
-          value: 33.74
-          verified: true
+pipeline_tag: text-generation
+base_model: HuggingFaceH4/zephyr-7b-beta
 widget:
-  - text: "<|system|>\nYou are a helpful assistant.</s>\n<|user|>\nThông tin về Peristernia despecta</s>\n<|assistant|>\n"
-    output:
-      text: "Peristernia despecta là một loài ốc biển, là động vật thân mềm chân bụng sống ở biển trong họ Fasciolariidae."
+- text: '<|system|>
+
+    You are a helpful assistant.</s>
+
+    <|user|>
+
+    Thông tin về Peristernia despecta</s>
+
+    <|assistant|>
+
+    '
+  output:
+    text: Peristernia despecta là một loài ốc biển, là động vật thân mềm chân bụng
+      sống ở biển trong họ Fasciolariidae.
+model-index:
+- name: lamhieu/ghost-7b-v0.9.0
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: VMLU
+      type: vmlu_v1.5
+    metrics:
+    - type: avg
+      value: 36.06
+      name: Average
+      verified: true
+    - type: stem
+      value: 33.54
+      name: STEM
+      verified: true
+    - type: ss
+      value: 38.74
+      name: Social science
+      verified: true
+    - type: hm
+      value: 37.15
+      name: Humanities
+      verified: true
+    - type: ot
+      value: 36.78
+      name: Other
+      verified: true
+  - task:
+      type: text-generation
+    dataset:
+      name: Open LLM Leaderboard
+      type: open_llm_leaderboard
+    metrics:
+    - type: avg
+      value: 56.89
+      name: Average
+      verified: true
+    - type: arc
+      value: 53.07
+      name: ARC
+      verified: true
+    - type: hs
+      value: 77.93
+      name: HellaSwag
+      verified: true
+    - type: hs
+      value: 77.93
+      name: HellaSwag
+      verified: true
+    - type: mmlu
+      value: 55.09
+      name: MMLU
+      verified: true
+    - type: wg
+      value: 73.72
+      name: Winogrande
+      verified: true
+    - type: gsm8k
+      value: 33.74
+      name: GSM8K
+      verified: true
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
+      name: Open LLM Leaderboard
+  - 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: 53.07
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
+      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: 77.93
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
+      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: 55.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
+      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: 47.79
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
+      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: 73.72
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
+      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: 33.74
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lamhieu/ghost-7b-v0.9.0
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Model ID
@@ -291,4 +402,17 @@ Many thanks for
 
 ## Model Card Contact
 
-**Lam H** ([email protected])
+**Lam H** ([email protected])
+# [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_lamhieu__ghost-7b-v0.9.0)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |56.89|
+|AI2 Reasoning Challenge (25-Shot)|53.07|
+|HellaSwag (10-Shot)              |77.93|
+|MMLU (5-Shot)                    |55.09|
+|TruthfulQA (0-shot)              |47.79|
+|Winogrande (5-shot)              |73.72|
+|GSM8k (5-shot)                   |33.74|
+