Adding Evaluation Results

README.md

@@ -1,10 +1,105 @@
 ---
-library_name: transformers
 license: apache-2.0
+library_name: transformers
 tags:
 - jamba
 - mamba
 - moe
+model-index:
+- name: Jamba-v0.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 20.26
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ai21labs/Jamba-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 10.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ai21labs/Jamba-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 0.98
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ai21labs/Jamba-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 2.46
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ai21labs/Jamba-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 3.71
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ai21labs/Jamba-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 16.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ai21labs/Jamba-v0.1
+      name: Open LLM Leaderboard
 ---
 
 # Model Card for Jamba
@@ -165,3 +260,17 @@ As a base model, Jamba is intended for use as a foundation layer for fine tuning
 AI21 builds reliable, practical, and scalable AI solutions for the enterprise.
 
 Jamba is the first in AI21’s new family of models, and the Instruct version of Jamba is coming soon to the [AI21 platform](https://www.ai21.com/studio). 
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ai21labs__Jamba-v0.1)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               | 9.10|
+|IFEval (0-Shot)    |20.26|
+|BBH (3-Shot)       |10.72|
+|MATH Lvl 5 (4-Shot)| 0.98|
+|GPQA (0-shot)      | 2.46|
+|MuSR (0-shot)      | 3.71|
+|MMLU-PRO (5-shot)  |16.45|
+