Adding Evaluation Results (#1)

- Adding Evaluation Results (1d32955a800b0a8a03f33857971432f7cdd8fb7a)


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

README.md

@@ -1,9 +1,12 @@
 ---
+language:
+- en
+- zh
 license: other
-license_name: tongyi-qianwen-research
-license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
 datasets:
 - Locutusque/UltraTextbooks-2.0
+license_name: tongyi-qianwen-research
+license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B/blob/main/LICENSE
 inference:
   parameters:
     do_sample: true
@@ -12,9 +15,109 @@ inference:
     top_k: 40
     max_new_tokens: 250
     repetition_penalty: 1.1
-language:
-- en
-- zh
+model-index:
+- name: tau-1.8B
+  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: 37.2
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/tau-1.8B
+      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: 60.26
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/tau-1.8B
+      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: 45.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/tau-1.8B
+      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: 39.72
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/tau-1.8B
+      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: 61.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/tau-1.8B
+      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: 30.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/tau-1.8B
+      name: Open LLM Leaderboard
 ---
 
 # tau-1.8B
@@ -52,4 +155,17 @@ The training of tau-1.8B required computational resources that contribute to the
 tau-1.8B was trained on a diverse dataset that may contain biases and inaccuracies. Users should be aware of these potential limitations and use the model responsibly. The model should not be used for tasks that could cause harm or discriminate against individuals or groups.
 
 ## Evaluation
-Coming Soon
+Coming Soon
+# [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_M4-ai__tau-1.8B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |45.73|
+|AI2 Reasoning Challenge (25-Shot)|37.20|
+|HellaSwag (10-Shot)              |60.26|
+|MMLU (5-Shot)                    |45.96|
+|TruthfulQA (0-shot)              |39.72|
+|Winogrande (5-shot)              |61.09|
+|GSM8k (5-shot)                   |30.17|
+