Adding Evaluation Results

README.md

@@ -1,5 +1,9 @@
 ---
 license: cc-by-nc-sa-4.0
+tags:
+- Composer
+- MosaicML
+- llm-foundry
 datasets:
 - camel-ai/code
 - ehartford/wizard_vicuna_70k_unfiltered
@@ -12,11 +16,110 @@ datasets:
 - jondurbin/airoboros-gpt4-1.2
 - LongConversations
 - camel-ai/physics
-tags:
-- Composer
-- MosaicML
-- llm-foundry
 inference: false
+model-index:
+- name: mpt-7b-8k-chat
+  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: 48.04
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-7b-8k-chat
+      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: 77.62
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-7b-8k-chat
+      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: 41.88
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-7b-8k-chat
+      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: 43.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-7b-8k-chat
+      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: 71.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-7b-8k-chat
+      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: 4.4
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mosaicml/mpt-7b-8k-chat
+      name: Open LLM Leaderboard
 ---
 
 # MPT-7B-Chat-8k
@@ -199,4 +302,17 @@ for open-source foundation models},
     note      = {Accessed: 2023-06-22},
     urldate   = {2023-06-22}
 }
-```
+```
+# [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_mosaicml__mpt-7b-8k-chat)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |47.78|
+|AI2 Reasoning Challenge (25-Shot)|48.04|
+|HellaSwag (10-Shot)              |77.62|
+|MMLU (5-Shot)                    |41.88|
+|TruthfulQA (0-shot)              |43.68|
+|Winogrande (5-shot)              |71.03|
+|GSM8k (5-shot)                   | 4.40|
+