初始化项目，由ModelHub XC社区提供模型

Model: hsefz-ChenJunJie/Deepseek-R1-Distill-NSFW-RPv1-mlx-fp16 Source: Original Platform
2026-05-11 12:53:47 +08:00
commit 08f5a5d8e8
11 changed files with 2513 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,35 @@
+---
+base_model: mergekit-community/Deepseek-R1-Distill-NSFW-RPv1
+library_name: transformers
+tags:
+- mergekit
+- merge
+- mlx
+- mlx-my-repo
+---
+
+# hsefz-ChenJunJie/Deepseek-R1-Distill-NSFW-RPv1-mlx-fp16
+
+The Model [hsefz-ChenJunJie/Deepseek-R1-Distill-NSFW-RPv1-mlx-fp16](https://huggingface.co/hsefz-ChenJunJie/Deepseek-R1-Distill-NSFW-RPv1-mlx-fp16) was converted to MLX format from [mergekit-community/Deepseek-R1-Distill-NSFW-RPv1](https://huggingface.co/mergekit-community/Deepseek-R1-Distill-NSFW-RPv1) using mlx-lm version **0.22.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("hsefz-ChenJunJie/Deepseek-R1-Distill-NSFW-RPv1-mlx-fp16")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```