| | --- |
| | language: |
| | - en |
| | license: apache-2.0 |
| | tags: |
| | - reasoning |
| | - instruct |
| | - 8b |
| | - 1kz |
| | - lfm-inspiration |
| | library_name: transformers |
| | pipeline_tag: text-generation |
| | inference: true |
| | --- |
| | |
| | # 1kz-Reasoning-8B |
| |
|
| | **A compact 8B reasoning model trained by 1kz** |
| | Strong at logical deduction, math, coding, multi-step problem solving, and long-context reasoning while staying efficient enough to run on a single consumer GPU. |
| |
|
| | ## Model Details |
| |
|
| | - **Developer**: [1kz](https://huggingface.co/1kz) |
| | - **Parameters**: 8.0B (dense) |
| | - **Context length**: 128K (RoPE scaled) |
| | - **Architecture**: Llama-3.1 style (same tokenizer & chat template as Meta-Llama-3.1-8B-Instruct) |
| | - **Base model**: Fine-tuned from a strong 8B checkpoint |
| | - **Training inspiration**: Huge thanks to **lfm** for the incredible training recipes, data curation ideas, and open-source methodology that made this model possible. Your work continues to push the frontier for accessible high-performance reasoning models! ❤️ |
| |
|
| | ## Intended Use |
| |
|
| | - Chain-of-thought reasoning |
| | - Complex math & science problems |
| | - Code generation + debugging |
| | - Agentic workflows |
| | - Research & education |
| |
|
| | ## Quick Start |
| |
|
| | ```python |
| | from transformers import pipeline |
| | |
| | pipe = pipeline( |
| | "text-generation", |
| | model="1kz/1kz-Reasoning-8B", |
| | device_map="auto", |
| | torch_dtype="auto" |
| | ) |
| | |
| | messages = [ |
| | {"role": "system", "content": "You are a world-class reasoning assistant."}, |
| | {"role": "user", "content": "Solve this step-by-step: A bat and a ball cost $1.10 in total. The bat costs $1.00 more than the ball. How much does the ball cost?"} |
| | ] |
| | |
| | output = pipe(messages, max_new_tokens=2048, temperature=0.7, do_sample=True) |
| | print(output[0]["generated_text"][-1]["content"]) |
