Text Generation
Transformers
Safetensors
mixtral
conversational
text-generation-inference
vicky4s4s commited on
Commit
c272d21
·
verified ·
1 Parent(s): 347fcc5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -32,3 +32,14 @@ The template used to build a prompt for the Instruct model is defined as follows
32
  <s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
33
  ```
34
  Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
 
 
 
 
 
 
 
 
 
 
 
 
32
  <s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
33
  ```
34
  Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
35
+
36
+
37
+ ## Limitations
38
+
39
+ The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance.
40
+ It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to
41
+ make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
42
+
43
+ ## Created:
44
+
45
+ Vignesh, [email protected]