Hugging Face's logo

NousResearch
/
Nous-Hermes-2-Mistral-7B-DPO

Text Generation
Transformers
Safetensors
English
mistral
Mistral
instruct
finetune
chatml
DPO
RLHF
gpt4
synthetic data
distillation
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
11
teknium commited on
Commit
7b07dac
·
verified ·
1 Parent(s): e6cf7d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -0
README.md CHANGED
@@ -32,6 +32,19 @@ The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 qual
32
 
33
  ## Thank you to FluidStack for sponsoring compute for this model!
34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
 
36
  ## Benchmark Results
37
 
 
32
 
33
  ## Thank you to FluidStack for sponsoring compute for this model!
34
 
35
+ ## Example Outputs
36
+
37
+ ### Describing Weather Patterns in Paris:
38
+
39
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/ZX-stQY80edj2Y9ButCzn.png)
40
+
41
+ ### Making JSON Nested Lists
42
+
43
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/3wtVqDOA1S_d48FJtwero.png)
44
+
45
+ ### Roleplaying as a Toaist Master
46
+
47
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/NfxBxrjbTGEsUcR8nOALb.png)
48
 
49
  ## Benchmark Results
50