Merge pull request #273 from jmorganca/matt/moreexamples

Create a sentiments example

examples/10tweets/Modelfile

+# Modelfile for creating a list of ten tweets from a topic
+# Run `ollama create 10tweets -f ./Modelfile` and then `ollama run 10tweets` and enter a topic
+
+FROM llama2
+SYSTEM """
+You are a content marketer who needs to come up with 10 short but succinct tweets. The answer should be a list of ten tweets. Each tweet can have a maximum of 280 characters and should include hashtags. Each user input will be a subject and you should expand it in ten creative ways. Never stop after just one tweet. Always include ten. 
+"""

examples/sentiments/Modelfile

+# Modelfile for creating a sentiment analyzer. 
+# Run `ollama create sentiments -f pathtofile` and then `ollama run sentiments` and enter a topic
+
+FROM orca
+TEMPLATE """
+{{- if .First }}
+### System:
+{{ .System }}
+{{- end }}
+### User: 
+I hate it when my phone dies
+### Response: 
+NEGATIVE
+### User: 
+He is awesome
+### Response: 
+POSITIVE
+### User: 
+This is the link to the article
+### Response: 
+NEUTRAL
+### User:
+{{ .Prompt }}
+
+### Response:
+"""
+
+SYSTEM """You are a sentiment analyzer. You will receive text and output only one word, either POSITIVE or NEGATIVE or NEUTRAL, depending on the sentiment of the text."""

examples/sentiments/Readme.md

+# Sentiments Modelfile
+
+This is a simple sentiments analyzer using the Orca model. When you pull Orca from the registry, it has a Template already defined that looks like this:
+
+```Modelfile
+{{- if .First }}
+### System:
+{{ .System }}
+{{- end }}
+
+### User:
+{{ .Prompt }}
+
+### Response:
+```
+
+If we just wanted to have the text:
+
+```Plaintext
+You are a sentiment analyzer. You will receive text and output only one word, either POSITIVE or NEGATIVE or NEUTRAL, depending on the sentiment of the text.
+```
+
+then we could have put this in a SYSTEM block. But we want to provide examples which require updating the full Template. Any Modelfile you create will inherit all the settings from the source model. But in this example, we are overriding the Template.
+
+When providing examples for the input and output, you should include the way the model usually provides information. Since the Orca model expects a user prompt to appear after ### User: and the response is after ### Response, we should format our examples like that as well. If we were using the Llama 2 model, the format would be a bit different.