From 977236e8916b3846364c75f1a0865a7249166dee Mon Sep 17 00:00:00 2001
From: JosefAlbers <146810011+JosefAlbers@users.noreply.github.com>
Date: Wed, 21 Aug 2024 10:02:02 +0900
Subject: [PATCH] phi-3.5-mini,-vision

---
 README.md           | 4 ++--
 phi_3_vision_mlx.py | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index 56d8a02..4ae5eea 100644
--- a/README.md
+++ b/README.md
@@ -4,8 +4,8 @@ Phi-3-MLX is a versatile AI framework that leverages both the Phi-3-Vision multi
 
 ## Features
 
-- Integration with Phi-3-Vision (multimodal) model
-- Support for the Phi-3-Mini-128K (language-only) model
+- Integration with [Phi-3.5-vision](https://huggingface.co/microsoft/Phi-3.5-vision-instruct) model
+- Support for the [Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) model
 - Optimized performance on Apple Silicon using MLX
 - Batched generation for processing multiple prompts
 - Flexible agent system for various AI tasks
diff --git a/phi_3_vision_mlx.py b/phi_3_vision_mlx.py
index 5dd1b1e..6052a8b 100644
--- a/phi_3_vision_mlx.py
+++ b/phi_3_vision_mlx.py
@@ -246,8 +246,8 @@ def to_lora(layer):
 
 def _setup():
     paths = [
-        ("microsoft/Phi-3-mini-128k-instruct", PATH_ORIGINAL_PHI3_BLIND, PATH_QUANTIZED_PHI3_BLIND),
-        ("microsoft/Phi-3-vision-128k-instruct", PATH_ORIGINAL_PHI3_VISION, PATH_QUANTIZED_PHI3_VISION)
+        ("microsoft/Phi-3.5-mini-instruct", PATH_ORIGINAL_PHI3_BLIND, PATH_QUANTIZED_PHI3_BLIND),
+        ("microsoft/Phi-3.5-vision-instruct", PATH_ORIGINAL_PHI3_VISION, PATH_QUANTIZED_PHI3_VISION)
     ]
     for hub, local, quant in paths:
         raw = snapshot_download(repo_id=hub, allow_patterns=["*.safetensors", "*.json"])
@@ -1221,7 +1221,7 @@ def benchmark(blind_model=False, json_path='benchmark.json'):
     """
     prompts = [
         ('Write a mystery horror.', ),
-        ('What is shown in this image?', 'https://assets-c4akfrf5b4d3f4b7.z01.azurefd.net/assets/2024/04/BMDataViz_661fb89f3845e.png'),
+        ('What is shown in this image?', 'https://collectionapi.metmuseum.org/api/collection/v1/iiif/344291/725918/main-image'),
         ([
             "Write an executive summary for a communications business plan",
             "Explain quantum computing.",