From ab8e376bc3601ef0528df786f224d33964d202aa Mon Sep 17 00:00:00 2001 From: Olivier DEBAUCHE Date: Sat, 2 Dec 2023 15:38:29 +0100 Subject: [PATCH] Add support for Med42 and PsyMedRP (#929) --- README.md | 2 ++ api/src/serge/data/models.json | 46 +++++++++++++++++++++++++++++++++- 2 files changed, 47 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 92ba2b1..4bbbc8f 100644 --- a/README.md +++ b/README.md @@ -60,12 +60,14 @@ Instructions for setting up Serge on Kubernetes can be found in the [wiki](https | **CodeLLaMA** | 7B, 13B | | **Falcon** | 7B, 7B-Instruct, 40B, 40B-Instruct | | **LLaMA** | 7B, 13B, 70B | +| **Med42** | 70B | | **Meditron** | 7B, 70B | | **Mistral** | 7B, 7B-Instruct, 7B-OpenOrca | | **Neural-Chat** | 7B-v3.1 | | **OpenChat** | 7B-v3.5 | | **OpenLLaMA** | 3B-v2, 7B-v2, 13B-v2 | | **Orca-2** | 7B, 13B | +| **PsyMedRP** | 13B-v1, 20B-v1 | | **Starling-LM** | 7B-Alpha | | **Vicuna** | 7B-v1.5, 13B-v1.5 | | **Zephyr** | 7B-Alpha, 7B-Beta | diff --git a/api/src/serge/data/models.json b/api/src/serge/data/models.json index bcb81b4..7d75bc7 100644 --- a/api/src/serge/data/models.json +++ b/api/src/serge/data/models.json @@ -1,4 +1,47 @@ [ + { + "name": "PsyMedRP", + "models": [ + { + "name": "PsyMedRP-v1-13B", + "repo": "TheBloke/PsyMedRP-v1-13B-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "psymedrp-v1-13b.Q4_K_M.gguf", + "disk_space": 7870000000.0 + } + ] + }, + { + "name": "PsyMedRP-v1-20B", + "repo": "TheBloke/PsyMedRP-v1-20B-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "psymedrp-v1-20b.Q4_K_M.gguf", + "disk_space": 12000000000.0 + } + ] + } + ] + }, + { + "name": "Med42", + "models": [ + { + "name": "Med42-70B", + "repo": "TheBloke/med42-70B-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "med42-70b.Q4_K_M.gguf", + "disk_space": 41400000000.0 + } + ] + } + ] + }, { "name": "Starling", "models": [ @@ -14,7 +57,8 @@ ] } ] - }, + }, + { "name": "Neural-Chat", "models": [