qwen-2.5-0.5b

f1eec9fa64a0c14e0ef2eec092b799009b3d4a1e · 2024-11-14 11:36:19 +0400 · Alex Cheema

Files touched

M exo/models.py

Diff

commit f1eec9fa64a0c14e0ef2eec092b799009b3d4a1e
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Thu Nov 14 11:36:19 2024 +0400

    qwen-2.5-0.5b
---
 exo/models.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/exo/models.py b/exo/models.py
index 22143752..0561220f 100644
--- a/exo/models.py
+++ b/exo/models.py
@@ -63,6 +63,7 @@ model_cards = {
   ### llava
   "llava-1.5-7b-hf": { "layers": 32, "repo": { "MLXDynamicShardInferenceEngine": "llava-hf/llava-1.5-7b-hf", }, },
   ### qwen
+  "qwen-2.5-0.5b": { "layers": 28, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-0.5B-Instruct-4bit", }, },
   "qwen-2.5-coder-1.5b": { "layers": 28, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-Coder-1.5B-Instruct-4bit", }, },
   "qwen-2.5-coder-3b": { "layers": 36, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-Coder-3B-Instruct-4bit", }, },
   "qwen-2.5-coder-7b": { "layers": 28, "repo": { "MLXDynamicShardInferenceEngine": "mlx-community/Qwen2.5-Coder-7B-Instruct-4bit", }, },

← fd867256 healthcheck · back to Exo · working versions d9aabd78 →