---
base_model: tiiuae/Falcon3-10B-Instruct
tags:
- fluently-lm
- fluently-sets
- demo
- reasoning
- thinking
- text-generation-inference
- transformers
- unsloth
- falcon3
- falcon
- llama
- trl
- sft
license: apache-2.0
language:
- en
datasets:
- fluently-sets/ultrathink
pipeline_tag: text-generation
---
# FalconThink3-10B Demo (Finetune of Falcon3-10B-IT on Ultrathink dataset)

***Q4_K_M GGUF-quant available [here](https://huggingface.co/fluently-sets/FalconThink3-10B-IT-Q4_K_M-GGUF)***

This is SFT-finetune Falcon3-10B-IT on Ultrathink dataset. This is far from a perfect model, its main purpose is to show an example of using the dataset.

- **Base model**: [tiiuae/Falcon3-10B-Instruct](https://huggingface.co/tiiuae/Falcon3-10B-Instruct)
- **Model type**: [LlamaForCausalLM](https://huggingface.co/models?other=llama)
- **Number of parameters**: 10.3B
- **Precision**: FP16
- **Training method**: SFT
- **Training dataset**: [fluently-sets/ultrathink](https://huggingface.co/datasets/fluently-sets/ultrathink)
- **Languages**: English (mostly)

*Trained by Fluently Team ([@ehristoforu](https://huggingface.co/ehristoforu)) with [Unsloth AI](https://github.com/unslothai/unsloth) with love🥰*

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)