evals

README.md

@@ -8,6 +8,26 @@ language:
 library_name: transformers
 license: llama3.1
 tags:
+- llama
+- llama3.1
+- llama3
+- meta
+- 70b
+- science
+- physics
+- biology
+- chemistry
+- compsci
+- computer-science
+- engineering
+- logic
+- rationality
+- advanced
+- expert
+- technical
+- conversational
+- chat
+- instruct
 - mergekit
 - merge
 pipeline_tag: text-generation
@@ -27,13 +47,148 @@ model-index:
     - type: acc
       value: 85.00
       name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: ARC Challenge (25-Shot)
+      type: arc-challenge
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 67.41
+      name: normalized accuracy
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Biology (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 93.75
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Biology (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 91.94
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU Conceptual Physics (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 82.13
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Physics (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 60.78
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Physics (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 62.25
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Chemistry (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 56.00
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Chemistry (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 73.40
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU Astronomy (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 89.47
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU College Computer Science (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.00
+      name: acc
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU High School Computer Science (5-Shot)
+      type: MMLU
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 90.00
+      name: acc
 
 ---
-# Untitled Model (1)
+# PlumChat 70b
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
 ## Merge Details
+
+Shining Valiant 2 + Nemotron for high quality general chat, science-instruct, and complex query performance.
+
 ### Merge Method
 
 This model was merged using the della merge method using [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) as a base.