A coding assistant with a 32k context window.
27 Pulls Updated 4 months ago
Updated 4 months ago
4 months ago
505af0d667d0 · 24GB
Readme
Model Summary
Purpose
A coding assistant optimized for Apple Silicon.
Key Features
- Advanced reasoning and coding capabilities.
Use Cases
- Designed for use with VSCode extension Continue or other Ollama-supported front ends.
Performance
No performance metrics provided yet.
Dependencies
- Requires Ollama or llama.cpp using the GGUF format.
- Recommended front end VSCode extension Continue
README
Installation Instructions
To run the latest version of the model, use the following command:
ollama run ih0dl/octopus:latest
Note: The vision model (ih0dl/octopus:vision
) will be available soon.
Usage Examples
You can prompt the model directly. For example, this octopus was prompted using the VS code extension and a context file:
Prompt: Can we change 'run_cli' in @sd3c.py to accept external variables?
Response:
Yes, you can modify the `run_cli()` function to accept external variables as arguments. Here's how you can do it:
```python
def run(frames, use_cyberpunk_palette, save_as_gif, output_path, blend_mode, save_faces, custom_prompt, negative_prompt, font_size, gif_frame_speed, use_existing_image, existing_image_path):
print("Welcome to the Cyberpunk Image Generator!")
main(
frames=frames,
use_cyberpunk_palette=use_cyberpunk_palette,
save_as_gif=save_as_gif,
output_path=output_path,
blend_mode=blend_mode,
save_simulated_vision=save_faces,
custom_prompt=custom_prompt,
font_size=font_size,
gif_frame_speed=gif_frame_speed,
use_existing_image=use_existing_image,
negative_prompt=negative_prompt,
existing_image_path=existing_image_path if use_existing_image else None
)
Now you can call the run()
function with your variables directly:
run(frames=4,
use_cyberpunk_palette=True,
save_as_gif=True,
output_path="./cypher_subjects/",
blend_mode="multiply",
save_faces=True,
custom_prompt="A close up of a woman's face in a photorealistic manner with high contrast and vivid colors against a black background",
negative_prompt="frame, border",
font_size=32,
gif_frame_speed=100,
use_existing_image=False,
existing_image_path=None)
Configuration Options
You should edit the system message and add in your device hardware. It will help the model immensely when suggesting commands.
Troubleshooting
There are no specific troubleshooting steps provided.
Contributors
Currently, the main contributor to this model is ih0dl.
License
This model is licensed under the Mistral AI Non-Production License.