From 36c1d8e8dcd42a7104ab532ef4ae003c08f41c5f Mon Sep 17 00:00:00 2001 From: madroid Date: Thu, 3 Oct 2024 03:36:07 +0800 Subject: [PATCH 1/2] Server: support function calling (#1003) --- llms/mlx_lm/server.py | 1 + 1 file changed, 1 insertion(+) diff --git a/llms/mlx_lm/server.py b/llms/mlx_lm/server.py index f2d8b86a..42962b54 100644 --- a/llms/mlx_lm/server.py +++ b/llms/mlx_lm/server.py @@ -594,6 +594,7 @@ class APIHandler(BaseHTTPRequestHandler): ): prompt = self.tokenizer.apply_chat_template( body["messages"], + body.get("tools", None), tokenize=True, add_generation_prompt=True, ) From 9bc53fc2100319d59179a179efe34346372772cf Mon Sep 17 00:00:00 2001 From: Awni Hannun Date: Wed, 2 Oct 2024 13:13:33 -0700 Subject: [PATCH 2/2] convert (#1006) --- whisper/convert.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/whisper/convert.py b/whisper/convert.py index da7195e0..cdd50bc5 100644 --- a/whisper/convert.py +++ b/whisper/convert.py @@ -35,6 +35,8 @@ _MODELS = { "large-v2": "https://openaipublic.azureedge.net/main/whisper/models/81f7c96c852ee8fc832187b0132e569d6c3065a3252ed18e56effd0b6a73e524/large-v2.pt", "large-v3": "https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt", "large": "https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt", + "large-v3-turbo": "https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt", + "turbo": "https://openaipublic.azureedge.net/main/whisper/models/aff26ae408abcba5fbf8813c21e62b0941638c5f6eebfb145be0c9839262a19a/large-v3-turbo.pt", } # base85-encoded (n_layers, n_heads) boolean arrays indicating the cross-attention heads that are @@ -52,6 +54,8 @@ _ALIGNMENT_HEADS = { "large-v2": b"ABzY8zd+h!0{>%R7=D0pU<_bnWW*tkYAhobTNnu$jnkEkXqp)j;w1Tzk)UH3X%SZd&fFZ2fC2yj", "large-v3": b"ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00", "large": b"ABzY8gWO1E0{>%R7(9S+Kn!D~%ngiGaR?*L!iJG9p-nab0JQ=-{D1-g00", + "large-v3-turbo": b"ABzY8j^C+e0{>%RARaKHP%t(lGR*)0g!tONPyhe`", + "turbo": b"ABzY8j^C+e0{>%RARaKHP%t(lGR*)0g!tONPyhe`", }