Hugging Face's logo

NousResearch
/
Nous-Hermes-2-Yi-34B

Text Generation
Transformers
Safetensors
English
llama
yi
instruct
finetune
chatml
gpt4
synthetic data
distillation
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
14
teknium commited on
Commit
6ec01ca
•
1 Parent(s): 8f32378

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -1
README.md CHANGED
@@ -28,8 +28,8 @@ Nous Hermes 2 Yi 34B was trained on 1,000,000 entries of primarily GPT-4 generat
28
 
29
  # Table of Contents
30
  1. [Example Outputs](#example-outputs)
 
31
  - Create a Flask based FTP Server
32
- -
33
  3. [Benchmark Results](#benchmark-results)
34
  - GPT4All
35
  - AGIEval
@@ -55,6 +55,22 @@ Nous Hermes 2 Yi 34B was trained on 1,000,000 entries of primarily GPT-4 generat
55
 
56
  Nous-Hermes 2 on Yi 34B outperforms all Nous-Hermes & Open-Hermes models of the past, achieving new heights in all benchmarks for a Nous Research LLM.
57
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  ## GPT4All
59
  GPT-4All Benchmark Set
60
  ```
 
28
 
29
  # Table of Contents
30
  1. [Example Outputs](#example-outputs)
31
+ - Discussing the Laws of Gravity
32
  - Create a Flask based FTP Server
 
33
  3. [Benchmark Results](#benchmark-results)
34
  - GPT4All
35
  - AGIEval
 
55
 
56
  Nous-Hermes 2 on Yi 34B outperforms all Nous-Hermes & Open-Hermes models of the past, achieving new heights in all benchmarks for a Nous Research LLM.
57
 
58
+ # Benchmarks Compared
59
+
60
+ ### GPT4All:
61
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/91onORUcUrAqTb3b9mG5e.png)
62
+
63
+ ### AGIEval:
64
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/hqDpMlKpINfDf4PmB31uW.png)
65
+
66
+ ### BigBench:
67
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/uh8mZZg_wZinFysxcfLSF.png)
68
+
69
+ ### TruthfulQA:
70
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/N_cX6YAWjJsvClotuoPdH.png)
71
+
72
+
73
+
74
  ## GPT4All
75
  GPT-4All Benchmark Set
76
  ```