b77cc86ae9b9d71a49aabe7fcd975d5a6089befd51fc49a57defc3f250d59813

README.md

@@ -8,7 +8,7 @@ tags:
 
 The Model [mlx-community/DeepSeek-R1-Distill-Qwen-1.5B-8bit](https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-1.5B-8bit) was
 converted to MLX format from [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B)
-using mlx-lm version **0.21.1**.
+using mlx-lm version **0.20.2**.
 
 ## Use with mlx
 
@@ -21,12 +21,12 @@ from mlx_lm import load, generate
 
 model, tokenizer = load("mlx-community/DeepSeek-R1-Distill-Qwen-1.5B-8bit")
 
-prompt = "hello"
+prompt="hello"
 
-if tokenizer.chat_template is not None:
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
     messages = [{"role": "user", "content": prompt}]
     prompt = tokenizer.apply_chat_template(
-        messages, add_generation_prompt=True
+        messages, tokenize=False, add_generation_prompt=True
     )
 
 response = generate(model, tokenizer, prompt=prompt, verbose=True)

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcaf9e5f931799b433d58ada2ab84d5c3dfc159f131a9029b06e350322d23c60
-size 1888373967
+oid sha256:a6ba6c1da3c96692bc9719e9e70973ec4e9193d79a2e4e49e6c183a017bab78e
+size 1888373799