From 77baec852c59daf8511d6f4d5219b48ab4fd6b94 Mon Sep 17 00:00:00 2001 From: Magnus Date: Sat, 19 Jul 2025 10:11:00 +0000 Subject: [PATCH] bring back README --- README.md | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index 68e0db5..44252a2 100644 --- a/README.md +++ b/README.md @@ -1,21 +1,20 @@ --- base_model: HuggingFaceTB/SmolLM2-360M tags: -- text-generation-inference - transformers - unsloth - llama license: apache-2.0 language: -- en +- de +datasets: +- wikimedia/wikipedia +- FreedomIntelligence/alpaca-gpt4-deutsch --- -# Uploaded finetuned model +# SmolLM2-360m-German-Instruct -- **Developed by:** mags0ft -- **License:** apache-2.0 -- **Finetuned from model :** HuggingFaceTB/SmolLM2-360M +This is a continued pre-train as well as an instruct fine-tune done using Unsloth in order to make SmolLM2 360m capable of speaking German. +It has been trained on 15% of the German Wikipedia as well as the full German version of the Alpaca-GPT4 dataset (translated version). -This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. - -[](https://github.com/unslothai/unsloth) +Even though a lot of training has been done, this is still a tiny model and is highly limited to its small size. Expect many hallucinations and do not use this in a demanding production workflow. \ No newline at end of file