TheBloke
/

Falcon-7B-Instruct-GGML

text-generation-inference

Model card Files Files and versions Community

TheBloke commited on Jul 7, 2023

Commit

7841c7d

•

1 Parent(s): 92e130a

Update README.md

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -35,12 +35,11 @@ For the previous ggmlv3 files, please see branch `ggmlv3`.
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/falcon-7B-instruct-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/tiiuae/falcon-7b-instruct)
-## Prompt template: Falcon
 ```
->>QUESTION<< PROMPT
->>ANSWER<<
 ```
 <!-- compatibility_ggml start -->

 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/falcon-7B-instruct-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/tiiuae/falcon-7b-instruct)
+## Prompt template
 ```
+User: prompt
+Assistant:
 ```
 <!-- compatibility_ggml start -->