Update README.md

README.md

@@ -1,6 +1,12 @@
 ---
 inference: false
-license: other
+license: cc-by-nc-sa-4.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+datasets:
+- psmathur/orca_minis_uncensored_dataset
 ---
 
 <!-- header start -->
@@ -34,6 +40,19 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/orca_mini_v2_7B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/psmathur/orca_mini_v2_7b)
 
+## Prompt template
+```
+### System:
+You are an AI assistant that follows instruction extremely well. Help as much as you can.
+
+### User:
+prompt
+
+### Input:
+
+### Response:
+```
+
 <!-- compatibility_ggml start -->
 ## Compatibility
 
@@ -87,7 +106,7 @@ Refer to the Provided Files table below to see what files use which methods, and
 I use the following command line; adjust for your tastes and needs:
 
 ```
-./main -t 10 -ngl 32 -m orca-mini-v2_7b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
+./main -t 10 -ngl 32 -m orca-mini-v2_7b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### System: You are an AI assistant that follows instruction extremely well. Help as much as you can.### User: Write a story about llamas\n### Response:"
 ```
 If you're able to use full GPU offloading, you should use `-t 1` to get best performance.