Downloads · 30 days
235
6% of all-time downloads
Aadeshisdoingsomething/Llama-3.2-1b-Claude-Gemini-reasoning
Llama-3.2-1b-Claude-Gemini-reasoning is a machine learning model from Aadeshisdoingsomething. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
[!CAUTION] This model is very stupid and makes up whatever it wants, i mainly made this just as a test to test an unsloth script. This model leans heavily into Llama 3.2 1b's creative tendencies, so it didn't become a…
Downloads · 30 days
235
6% of all-time downloads
All-time downloads
4.1K
Public
Repo size
808 MB
Likes
1
Public
Click a slice to open those files.
.gguf808 MB · 100%
From the Hugging Face model README
[!CAUTION] This model is very stupid and makes up whatever it wants, i mainly made this just as a test to test an unsloth script. This model leans heavily into Llama 3.2 1b's creative tendencies, so it didn't become any better, if not became worse at reasoning tasks.
Trained with: https://github.com/aadeshisdoingsomething/train-model-unsloth/tree/main
This model was finetuned and converted to GGUF format using Unsloth.
From my testing, the only good usecase is to mimic the style of output and reasoning of larger models like claude 4.6 opus. Beyond that, it keeps llama's "yes-man" style and has no clue what it is doing.
Aadeshisdoingsomething/claude-gemini-reasoning <br /> TeichAI/claude-haiku-4.5-1700x
Example usage:
./llama.cpp/llama-cli -hf Aadeshisdoingsomething/Llama-3.2-1b-Claude-Gemini-reasoning-GGUF --jinja./llama.cpp/llama-mtmd-cli -hf Aadeshisdoingsomething/Llama-3.2-1b-Claude-Gemini-reasoning-GGUF --jinjallama-3.2-1b-instruct.Q4_K_M.ggufAn Ollama Modelfile is included for easy deployment. This was trained 2x faster with Unsloth <img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>