#smollm2 — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #smollm2, aggregated by home.social.
-
Today I just want to quote smollm2:1.7b by HuggingFace:
"I don't know what to say, so I'll just say this:
Merry Christmas!"hf_commit_hash=80befba1f034a5408e46a9aa03834e804170d7dc
prompt="Merry Christmas to you!"
seed=42
temperature=0.4
do_sample=true
num_beams=1
max length=50
top_k=50
top_p=0.1#huggingface #llm #smollm #smollm2 #python #torch #transformers #ai #citation #quote #quotes #commit #merrychristmas #merryxmas #christmas #tech #programming
-
Hugging Face's SmolLM2 is a new family of compact language models that outperform Llama 3.2 and Qwen 2.5 on various benchmarks, available in sizes of 135M, 360M, and 1.7B parameters.
I just tested the 135M version with #ollama; it's very fast but not particularly intelligent, making it better suited for simpler tasks like text classification or data preprocessing, especially since it supports tool use.
#smollm2 #huggingface #ollama #llm #ai #programming #compact #llama #qwen #benchmarks
