diff --git a/README.md b/README.md index 4c13a85..d0781b5 100644 --- a/README.md +++ b/README.md @@ -57,9 +57,10 @@ Instructions for setting up Serge on Kubernetes can be found in the [wiki](https | Category | Models | |:-------------:|:-------| +| **Alfred** | 40B | | **CodeLLaMA** | 7B, 13B | | **Falcon** | 7B, 7B-Instruct, 40B, 40B-Instruct | -| **LLaMA** | 7B, 13B, 70B | +| **LLaMA 2** | 7B, 13B, 70B | | **Med42** | 70B | | **Meditron** | 7B, 70B | | **Mistral** | 7B, 7B-Instruct, 7B-OpenOrca | diff --git a/api/src/serge/data/models.json b/api/src/serge/data/models.json index d0f9d1b..da8bbfa 100644 --- a/api/src/serge/data/models.json +++ b/api/src/serge/data/models.json @@ -1,4 +1,20 @@ [ + { + "name": "Alfred", + "models": [ + { + "name": "Alfred-40B", + "repo": "TheBloke/alfred-40B-1023-GGUF", + "files": [ + { + "name": "q4_K_M", + "filename": "alfred-40b-1023.Q4_K_M.gguf", + "disk_space": 25500000000.0 + } + ] + } + ] + }, { "name": "PsyMedRP", "models": [