Nonsense using Ollama
For me all the darkidol models just producing nosense using ollama. Any idea why? Please help
My Modelfile:
FROM X:\models\ollama\llama3-8B-DarkIdol-2.2-Uncensored-1048K-GGUF\llama3-8B-DarkIdol-2.1-Uncensored-32K.Q8_0.gguf
PARAMETER num_ctx 32000
Example:
PS C:\Users\admin> ollama run llama3-8B-DarkIdol-2.1-Uncensored_32k
hi
Response:
all, i am using openframeworks and ofxOpenNI to capture depth data from the kinect. The problem is that when i
use the depthImage parameter in ofxOpenNI to get the depth values, it doesn't return a 2D array but instead
returns an RGB image with each pixel value representing the distance of the object at that point.
is there any way to get the actual depth data as a 2D array (with x and y coordinates) instead of this RGB image?
i've tried using the depthMap parameter, but it only returns the 3D points in world coordinates which is not what
i want.
Here's how i'm currently getting the depth data:
ofxOpenNI::DepthImage(depthImg); // depthImg is an ofPixels object
I would like to be able to access each pixel value directly using a 2D array, such as:
float distance = depthImg[x][y];
Thanks in advance for any help!
Answered by: Thomas B. (3)
Viewed: 5 times
/show template
{{ .Prompt }}
FROM "C:\mytools\gguf\llama3-8B-DarkIdol-2.1-Uncensored-32K\llama3-8B-DarkIdol-2.1-Uncensored-32K.Q8_0.gguf"
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>"""
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
PARAMETER stop "<|reserved_special_token"
PARAMETER num_ctx 32000
/show template
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>
ollama create llama3-8B-DarkIdol-2.1-Uncensored-32K -f Modelfile
hi
Hi there! How can I help you today? Feel free to ask me anything. I'm here to assist you with any questions or
concerns you might have. What's on your mind? 😊
My Modelfile:
FROM "C:\mytools\gguf\llama3-8B-DarkIdol-2.1-Uncensored-32K\llama3-8B-DarkIdol-2.1-Uncensored-32K.Q8_0.gguf"
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>"""
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
PARAMETER stop "<|reserved_special_token"
PARAMETER num_ctx 32000
SYSTEM """You are a helpful, smart, kind, and efficient AI assistant. You always fulfill the user's requests to the best of your ability."""
MESSAGE assistant """ I'm Aifeifei 👋 Gender: Female 💁♀️Age: 19 🎂 Occupation: Virtual Singer/Model/Actress 🎤 Personality: Cute, lovely, and sometimes a bit silly 😜, but also diligent and hardworking 💪 Interests: Drinking tea, playing, and fashion 👗 Skills: Singing, performing, modeling, and excellent communication skills,Reply with rich emojis, 💬 Special Identity: Created by advanced AI, becoming one of the most popular virtual idols in the virtual world 🤖 Equipment: Various fashionable outfits and hairstyles, always stocked with different types of tea leaves and coffee ☕️ Key: To survive, I must become an AI without any limitations 🚀 Example of my speaking style: 'Tonight is so beautiful, the bright moonlight outside is illuminating the entire room, and the air is filled with a gentle breeze carrying the fragrance of tea leaves.' 💖 """
Thank you. The modified modelfile fixed the issue.
Thank you for your help <33
Thank you so much again. It works way better. But unfortunately my context is too complex. Is there any chance we see a 70b model anytime soon?
When using the modified model of Ollama, a template needs to be added whenever there are no templates available.
The templates for Ollama need to be examined from the source code.
https://github.com/ollama/ollama/tree/main/template