LocalAI/docs/content/docs
Ettore Di Giacinto bc8f648a91
fix(doc/examples): set defaults to mirostat (#1820)
The default sampler on some models don't return enough candidates which
leads to a false sense of randomness. Tracing back the code it looks
that with the temperature sampler there might not be enough
candidates to pick from, and since the seed and "randomness" take effect
while picking a good candidate this yields to the same results over and
over.

Fixes https://github.com/mudler/LocalAI/issues/1723 by updating the
examples and documentation to use mirostat instead.
2024-03-11 19:49:03 +01:00
..
advanced fix(doc/examples): set defaults to mirostat (#1820) 2024-03-11 19:49:03 +01:00
features Bump vLLM version + more options when loading models in vLLM (#1782) 2024-03-01 22:48:53 +01:00
getting-started feat(sycl): Add support for Intel GPUs with sycl (#1647) (#1660) 2024-02-01 19:21:52 +01:00
reference Drop ggml-based gpt2 and starcoder (supported by llama.cpp) (#1679) 2024-02-04 13:15:51 +01:00
faq.md docs: re-use original permalinks (#1610) 2024-01-19 19:23:58 +01:00
integrations.md Edit links in readme and integrations page (#1796) 2024-03-05 10:14:30 +01:00
overview.md Update overview.md 2024-02-28 15:24:08 +01:00
whats-new.md docs/examples: enhancements (#1572) 2024-01-18 19:41:08 +01:00