From 0b433dd42878674e70a3511606b028625e76915b Mon Sep 17 00:00:00 2001 From: Marcel Klehr Date: Tue, 28 Jan 2025 11:01:24 +0100 Subject: [PATCH 1/3] enh(ai/llm2): Document OLMo as a fully open model Signed-off-by: Marcel Klehr --- admin_manual/ai/app_llm2.rst | 25 ++++++++++++++++++++++++- 1 file changed, 24 insertions(+), 1 deletion(-) diff --git a/admin_manual/ai/app_llm2.rst b/admin_manual/ai/app_llm2.rst index 4a7e55dd117..44b17f1843a 100644 --- a/admin_manual/ai/app_llm2.rst +++ b/admin_manual/ai/app_llm2.rst @@ -129,4 +129,27 @@ Known Limitations * Language models are likely to generate false information and should thus only be used in situations that are not critical. It's recommended to only use AI at the beginning of a creation process and not at the end, so that outputs of AI serve as a draft for example and not as final product. Always check the output of language models before using it. * Make sure to test the language model you are using it for whether it meets the use-case's quality requirements * Language models notoriously have a high energy consumption, if you want to reduce load on your server you can choose smaller models or quantized models in exchange for lower accuracy -* Customer support is available upon request, however we can't solve false or problematic output, most performance issues, or other problems caused by the underlying model. Support is thus limited only to bugs directly caused by the implementation of the app (connectors, API, front-end, AppAPI) \ No newline at end of file +* Customer support is available upon request, however we can't solve false or problematic output, most performance issues, or other problems caused by the underlying model. Support is thus limited only to bugs directly caused by the implementation of the app (connectors, API, front-end, AppAPI) + +Addendum: Running with a fully open model +----------------------------------------- + +If you would like to use a fully open model that scores a green score on our Ethical AI rating, we recommend the following model: + +* OLMo 2 (either in 7B or 14B): ``_ + +What makes OLMo a fully open model? +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +* The code for training, fine-tuning and inference of the model is publicly available nad fully open source +* The training data with which the model is pretrained is publicly available +* The model itself is publicly available and fully open source +* The instruction tuning data is publicly available +* The Reinforcement learning model is publicly available and fully open source + +Limitations +~~~~~~~~~~~ + +* OLMo currently only works well with English language input +* In our tests it sometimes produced hallucinated or garbled output; make sure to thoroughly test the model for your use case +* It cannot use tools, so cannot be used in conjunction with :ref:`Context Agent ` From 2b0fb431727125fa238358e39aed0e29983e3c9d Mon Sep 17 00:00:00 2001 From: Marcel Klehr Date: Fri, 31 Jan 2025 13:09:56 +0100 Subject: [PATCH 2/3] Fix: Update admin_manual/ai/app_llm2.rst Co-authored-by: Julien Veyssier Signed-off-by: Marcel Klehr --- admin_manual/ai/app_llm2.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/admin_manual/ai/app_llm2.rst b/admin_manual/ai/app_llm2.rst index 44b17f1843a..fa72684ad23 100644 --- a/admin_manual/ai/app_llm2.rst +++ b/admin_manual/ai/app_llm2.rst @@ -141,7 +141,7 @@ If you would like to use a fully open model that scores a green score on our Eth What makes OLMo a fully open model? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -* The code for training, fine-tuning and inference of the model is publicly available nad fully open source +* The code for training, fine-tuning and inference of the model is publicly available and fully open source * The training data with which the model is pretrained is publicly available * The model itself is publicly available and fully open source * The instruction tuning data is publicly available From ca626b7658a001710e32239b3c852f25746a56db Mon Sep 17 00:00:00 2001 From: Marcel Klehr Date: Fri, 31 Jan 2025 13:10:07 +0100 Subject: [PATCH 3/3] Fix: Update admin_manual/ai/app_llm2.rst Co-authored-by: Anupam Kumar Signed-off-by: Marcel Klehr --- admin_manual/ai/app_llm2.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/admin_manual/ai/app_llm2.rst b/admin_manual/ai/app_llm2.rst index fa72684ad23..709b6c71599 100644 --- a/admin_manual/ai/app_llm2.rst +++ b/admin_manual/ai/app_llm2.rst @@ -136,7 +136,7 @@ Addendum: Running with a fully open model If you would like to use a fully open model that scores a green score on our Ethical AI rating, we recommend the following model: -* OLMo 2 (either in 7B or 14B): ``_ +* OLMo 2 (either in 7B or 13B): ``_ What makes OLMo a fully open model? ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~