Instructions to use joermd/speedy_think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use joermd/speedy_think with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("joermd/speedy_think", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
|
Download README.md from joermd/speedy_think: direct link, hf CLI and curl.
- Browser
- Download file 625 Bytes
-
https://huggingface.co/joermd/speedy_think/resolve/b4526ccc9f90b1bcac21fe3ce44fbb32fd47326e/README.md
- Command line
-
hf download hf://joermd/speedy_think@b4526ccc9f90b1bcac21fe3ce44fbb32fd47326e/README.md
-
curl -L -o README.md https://huggingface.co/joermd/speedy_think/resolve/b4526ccc9f90b1bcac21fe3ce44fbb32fd47326e/README.md
625 Bytes
metadata
base_model: unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
Uploaded model
- Developed by: joermd
- License: apache-2.0
- Finetuned from model : unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
