|
--- |
|
base_model: Qwen/Qwen2.5-14B-Instruct |
|
tags: |
|
- fluently-lm |
|
- fluently-sets |
|
- demo |
|
- reasoning |
|
- text-generation-inference |
|
- transformers |
|
- unsloth |
|
- qwen2 |
|
- trl |
|
- sft |
|
license: apache-2.0 |
|
language: |
|
- en |
|
datasets: |
|
- fluently-sets/reasoning-1-1k |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# Reasoning-1 1K Demo (Finetune of Qwen2.5-14B-IT on Reasoning-1-1k dataset) |
|
|
|
***Q4_K_M GGUF-quant available [here](https://huggingface.co/fluently-sets/reasoning-1-1k-demo-Q4_K_M-GGUF)*** |
|
|
|
This is SFT-finetune Qwen2.5-14B-IT on Reasoning-1-1K dataset. This is far from a perfect model, its main purpose is to show an example of using the dataset. |
|
|
|
- **Base model**: [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct) |
|
- **Model type**: [Qwen2ForCausalLM](https://huggingface.co/models?other=qwen2) |
|
- **Number of parameters**: 14.8B |
|
- **Precision**: FP16 |
|
- **Training method**: SFT |
|
- **Training dataset**: [fluently-sets/reasoning-1-1k](https://huggingface.co/datasets/fluently-sets/reasoning-1-1k) |
|
- **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) |
