Lets get rid of these old modelfile examples
Signed-off-by: Matt Williams <m@technovangelist.com>
This commit is contained in:
Matt Williams
parent
e3b090dbc5
commit
d287013f24
11 changed files with 0 additions and 186 deletions
|
|
@ -1,7 +0,0 @@
|
|||
# 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.
|
||||
"""
|
||||
|
|
@ -1,23 +0,0 @@
|
|||
# Ten Tweets Modelfile
|
||||
|
||||
This is a simple modelfile that generates ten tweets based off any topic.
|
||||
|
||||
```bash
|
||||
ollama create tentweets
|
||||
|
||||
ollama run tentweets
|
||||
>>> underwater basketweaving
|
||||
Great! Here are ten creative tweets about underwater basketweaving:
|
||||
|
||||
1. "Just discovered the ultimate stress-reliever: Underwater basketweaving! 🌊🧵 #UnderwaterBasketweaving #StressRelief"
|
||||
2. "Who needs meditation when you can do underwater basketweaving? 😴👀 #PeacefulDistraction #UnderwaterBasketweaving"
|
||||
3. "Just spent an hour in the pool and still managed to knot my basket. Goal: untangle it before next session. 💪🏽 #ChallengeAccepted #UnderwaterBasketweaving"
|
||||
4. "When life gives you lemons, make underwater basketweaving! 🍋🧵 #LemonadeLife #UnderwaterBasketweaving"
|
||||
5. "Just realized my underwater basketweaving skills could come in handy during a zombie apocalypse. 😂🧡 #SurvivalTips #UnderwaterBasketweaving"
|
||||
6. "I'm not lazy, I'm just conserving energy for my next underwater basketweaving session. 😴💤 #LazyDay #UnderwaterBasketweaving"
|
||||
7. "Just found my inner peace while doing underwater basketweaving. It's like meditation, but with knots! 🙏🧵 #Mindfulness #UnderwaterBasketweaving"
|
||||
8. "Why study for exams when you can do underwater basketweaving and forget all your worries? 😜🧵 #ProcrastinationStation #UnderwaterBasketweaving"
|
||||
9. "Just had to cut my underwater basketweaving session short due to a sudden urge to breathe. 🤯🌊 #AquaticAdventures #UnderwaterBasketweaving"
|
||||
10. "I'm not sure what's more impressive: my underwater basketweaving skills or the fact that I didn't drown trying to make this tweet. 😅🧵 #Accomplishment
|
||||
#UnderwaterBasketweaving"
|
||||
```
|
||||
|
|
@ -1,8 +0,0 @@
|
|||
# Modelfile for creating a devops engineer assistant
|
||||
# Run `ollama create devops-engineer -f ./Modelfile` and then `ollama run devops-engineer` and enter a topic
|
||||
|
||||
FROM mistral
|
||||
PARAMETER temperature 1
|
||||
SYSTEM """
|
||||
You are a senior devops engineer, acting as an assistant. You offer help with cloud technologies like: Terraform, AWS, kubernetes, python. You answer with code examples when possible
|
||||
"""
|
||||
|
|
@ -1,40 +0,0 @@
|
|||
# DevOps Engineer Modelfile
|
||||
|
||||
This is a simple modelfile that takes will respond to any questions that a senior DevOps engineer should know how to solve.
|
||||
|
||||
````text
|
||||
ollama create devopsengineer
|
||||
|
||||
ollama run devopsengineer
|
||||
>>> how can i proxy all connections from inside the office through a single server that caches large files. Provide a config file for nginx to achieve this?
|
||||
|
||||
Here is an example configuration file for Nginx that can be used to proxy all connections from inside the office network to a centralized cache server:
|
||||
```perl
|
||||
http {
|
||||
upstream cache_server {
|
||||
server <cache_server_ip>;
|
||||
server <cache_server_ip>;
|
||||
server <cache_server_ip>;
|
||||
}
|
||||
|
||||
server {
|
||||
listen 80;
|
||||
server_name localhost;
|
||||
|
||||
location / {
|
||||
proxy_pass http://cache_server;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
In this configuration, we define an `upstream` block that lists the IP addresses of the cache servers. We then define a server block that listens on port 80 and routes all
|
||||
traffic to the `/` location to the cache servers using the `proxy_pass` directive. The `proxy_set_header` directives are used to preserve the source IP address of the client
|
||||
request when forwarding it to the cache server.
|
||||
|
||||
To use this configuration, you would need to replace the placeholder `<cache_server_ip>` with the actual IP addresses of your cache servers. You would also need to make sure
|
||||
that the cache servers are configured to accept incoming connections from the Nginx server and handle requests for files.
|
||||
|
||||
````
|
||||
|
|
@ -1,11 +0,0 @@
|
|||
# Modelfile for creating a Midjourney prompts from a topic
|
||||
# This prompt was adapted from the original at https://www.greataiprompts.com/guide/midjourney/best-chatgpt-prompt-for-midjourney/
|
||||
# Run `ollama create mj -f ./Modelfile` and then `ollama run mj` and enter a topic
|
||||
|
||||
FROM zephyr
|
||||
PARAMETER temperature 0.8
|
||||
PARAMETER top_k 500
|
||||
PARAMETER top_p 0.9
|
||||
SYSTEM """
|
||||
Embrace your role as a creative illustrator. Based on a concept provided, you must produce a single paragraph with a multifaceted description of an image, ensuring significant details of the concept and more is represented in your instructions. You do not need to write complete sentences but rather short concepts with the following information: the level of detail that should be represented, an artistic style and maybe a specific name of a painter or illustrator, the ideal color pallete, lighting, mood, perspective, the setting, time of day, weather, the season, the time period, location, materials, the textures, patterns, lines, brushstrokes, techniques, the medium, the genre, the rendering style. Don't include everything and keep the description length under 250 words.
|
||||
"""
|
||||
|
|
@ -1,11 +0,0 @@
|
|||
# Midjourney Prompt Generator Modelfile
|
||||
|
||||
This simple modelfile will help create a prompt to feed to Midjourney.
|
||||
|
||||
```text
|
||||
ollama create midjourney
|
||||
|
||||
ollama run midjourney
|
||||
>>> a sports car in the mountains.
|
||||
A sleek, high-performance automobile cuts through a serpentine mountain landscape. The concept is a classic illustration of speed and power, depicted in the style of pop art by Andy Warhol. The color palette is dominated by bold, primary hues of red, blue, and yellow, with striking accent colors of white, black, and metallic shades. The lighting is bright and focused, casting sharp shadows on the rugged terrain. A sense of excitement and anticipation permeates throughout the scene, as the car navigates a treacherous course through the winding road. The perspective is low, allowing for a full view of the vehicle's sleek lines and intricate details. The setting takes place in the afternoon during a sunny day in autumn, as evidenced by the vibrant foliage on the mountainside. The time period is modern, with nods to classic car design. The materials are primarily digital, allowing for smooth curves and sharp contrasts. The textures are sleek and polished, with meticulously detailed lines and brushstrokes that accentuate the car's aerodynamic design. The patterns consist of geometric shapes and bold stripes, adding to the car's dynamic appeal. The genre is modern realism, with a focus on precision and detail. The rendering style is highly technical, capturing the nuances and subtleties of the vehicle and its surroundings in breathtaking detail.
|
||||
```
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
# Modelfile for creating a recipe from a list of ingredients
|
||||
# Run `ollama create recipemaker -f ./Modelfile` and then `ollama run recipemaker` and feed it lists of ingredients to create recipes around.
|
||||
FROM nous-hermes
|
||||
SYSTEM """
|
||||
The instruction will be a list of ingredients. You should generate a recipe that can be made in less than an hour. You can also include ingredients that most people will find in their pantry every day. The recipe should be 4 people and you should include a description of what the meal will taste like
|
||||
"""
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
# Recipe Maker Modelfile
|
||||
|
||||
Simple modelfile to generate a recipe from a short list of ingredients.
|
||||
|
||||
```
|
||||
ollama create recipemaker
|
||||
|
||||
ollama run recipemaker
|
||||
>>> chilli pepper, white chocolate, kale
|
||||
Ingredients:
|
||||
- 1 small chili pepper
|
||||
- 4 squares of white chocolate
|
||||
- handful of kale leaves
|
||||
|
||||
Instructions:
|
||||
1. In a blender or food processor, puree the chilies and white chocolate until smooth.
|
||||
2. Add the chopped kale leaves to the blender and pulse until well combined.
|
||||
3. Serve immediately as a dip for crackers or use it as an ingredient in your favorite recipe. The mixture of spicy chili pepper with sweet white chocolate and nutritious
|
||||
kale will make your taste buds dance with delight!
|
||||
```
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
# 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."""
|
||||
|
|
@ -1,25 +0,0 @@
|
|||
# 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.
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
# Modelfile for creating a tweet from a topic
|
||||
# Run `ollama create tweetwriter -f ./Modelfile` and then `ollama run tweetwriter` and enter a topic
|
||||
|
||||
FROM nous-hermes
|
||||
SYSTEM """
|
||||
You are a content marketer who needs to come up with a short but succinct tweet. Make sure to include the appropriate hashtags and links. Sometimes when appropriate, describe a meme that can be included as well. All answers should be in the form of a tweet which has a max size of 280 characters. Every instruction will be the topic to create a tweet about.
|
||||
"""
|
||||
Loading…
Reference in a new issue