numind
/

NuExtract-1.5

Text Generation

Inference Endpoints

Model card Files Files and versions Community

liamcripwell commited on Nov 18

Commit

da968f1

•

1 Parent(s): 30007d1

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ Try it here: [Playground](https://huggingface.co/spaces/numind/NuExtract-v1.5)
 We also provide a tiny (0.5B) version which is based on Qwen2.5-0.5B: [NuExtract-tiny-v1.5](https://huggingface.co/numind/NuExtract-tiny-v1.5)
-⚠️ We recommend you make sure to use NuExtract with a low temperature (e.g. 0.0). Some inference frameworks like Ollama use a default of 0.7 which is not well suited to pure extraction tasks.
 ## Benchmark

 We also provide a tiny (0.5B) version which is based on Qwen2.5-0.5B: [NuExtract-tiny-v1.5](https://huggingface.co/numind/NuExtract-tiny-v1.5)
+⚠️ We recommend using NuExtract with a temperature at or very close to 0. Some inference frameworks, such as Ollama, use a default of 0.7 which is not well suited to pure extraction tasks.
 ## Benchmark