cmarkea
/

Mixtral-8x7B-Instruct-v0.1-4bit

Text Generation

Mixture of Experts

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Cyrile commited on Feb 5

Commit

bc2e5de

•

1 Parent(s): 406bbb2

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -15,5 +15,5 @@ Converted version of [Mixtral Instruct](https://huggingface.co/mistralai/Mixtral
 ### Prompt Pattern
 Here is a reminder of the command pattern to interact with the model if the add_special_tokens option is disabled (otherwise, do not include the BOS symbol and space at the beginning of the sequence):
 ```verbatim
-<s> [INST] {user_prompt_1} [/INST] model_answer_1</s>[INST] {user_prompt_2} [/INST] model_answer_2</s>
 ```

 ### Prompt Pattern
 Here is a reminder of the command pattern to interact with the model if the add_special_tokens option is disabled (otherwise, do not include the BOS symbol and space at the beginning of the sequence):
 ```verbatim
+<s> [INST] {user_prompt_1} [/INST] model_answer_1</s> [INST] {user_prompt_2} [/INST] model_answer_2</s>
 ```