---
license: apache-2.0
datasets:
- GrainWare/tuxsentience
language:
- en
base_model:
- unsloth/Qwen3-0.6B
pipeline_tag: text-generation
---

# DISCLAIMER: DO NOT USE THIS IN PUBLIC DEPLOYMENTS WE ARE NOT RESPONSIBLE FOR WHAT THIS MODEL IN PARTICULAR SAYS
# THIS IS AN EXPERIMENT

# graig-code-turbo-fast-slow-4.5-mini

the latest state of the art model in the field of accuracy

other companies may be trying to reach artificial general intelligence, but we are trying to reach artificial grain intelligence. with the help of our team of the best grain farmers in the world, we are making huge strides in the field. fine tuned fully locally using a RX 9070 XT using unsloth.

`ollama run hf.co/electron271/graig-code-turbo-fast-slow-4.5-mini:F16`

## Recommended Settings

- **`temperature = 0.6`**
- `top_k = 20`
- `min_p = 0.00` (llama.cpp's default is 0.1)
- **`top_p = 0.95`**
- `presence_penalty = 0.0 to 2.0` (llama.cpp default turns it off, but to reduce repetitions, you can use this) Try 1.0 for example.
- Supports up to `131,072` context natively but you can set it to `32,768` tokens for less RAM use

you can also use `/no_think` for extra chaoticness