pythink-qwen2-1.5b-v0.0.1-safetensors/README.md

license, language, base_model, tags, pipeline_tag, library_name

license	language	base_model	tags	pipeline_tag	library_name
mit	en	WeiboAI/VibeThinker-1.5B	gguf llama.cpp unsloth math code gpqa reasoning python	text-generation	transformers

PyThink-1.5B v0.0.1 : safetensors

🚨 This model was built to output "reasoning plans" in Python, and does not always output normal responses. This model is intended for research into alternative ways to make LLMs do structured reasoning.

This model was made to generate more training data and to start experimenting with LLM reasoning in code. Code executes faster and with less compute than LLMs, is deterministic, and is easier to audit. This small model can run on my laptop, is blazing fast, and is already close to good for generating new training data.

I will be releasing more versions soon.

• Training dataset: https://huggingface.co/datasets/NuclearManD/pythink-20k

• GGUF 4bit quantized version: https://huggingface.co/NuclearManD/pythink-qwen2-1.5b-v0.0.1-Q4_K_M-GGUF

Follow me on X for updates: https://x.com/NuclearManD

This model was finetuned and converted using Unsloth.

Example usage:

• For text only LLMs: llama-cli -hf NuclearManD/pythink-qwen2-1.5b-v0.0.1-Q4_K_M-GGUF --jinja

Available Model files:

• checkpoint-360.Q4_K_M.gguf This was trained 2x faster with Unsloth

Fine-tuned from (WeiboAI/VibeThinker-1.5B)[https://huggingface.co/WeiboAI/VibeThinker-1.5B].

License

The model repository is licensed under the MIT License.