Hugging Face's logo

NousResearch
/
Nous-Hermes-2-Mixtral-8x7B-DPO

Text Generation
Transformers
Safetensors
English
mixtral
Mixtral
instruct
finetune
chatml
DPO
RLHF
gpt4
synthetic data
distillation
conversational
text-generation-inference
Model card Files Community
14
teknium commited on
Commit
cb6a003
·
verified ·
1 Parent(s): 2eb41a4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -133,12 +133,15 @@ Average: 49.70
133
 
134
  ## GPT4All
135
 
 
136
 
137
  ## AGI-Eval
138
 
 
139
 
140
  ## BigBench Reasoning Test
141
 
 
142
 
143
  ## Comparison to Mixtral Instruct:
144
 
 
133
 
134
  ## GPT4All
135
 
136
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/HK6bSbMfxX_qzxReAcJH9.png)
137
 
138
  ## AGI-Eval
139
 
140
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/bs3ZvvEACa5Gm4p1JBsZ4.png)
141
 
142
  ## BigBench Reasoning Test
143
 
144
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/wcceowcVpI12UxliwkOja.png)
145
 
146
  ## Comparison to Mixtral Instruct:
147