初始化项目，由ModelHub XC社区提供模型

Model: alexgusevski/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-fp16
Source: Original Platform

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+datasets:
+- TeichAI/claude-4.5-opus-high-reasoning-250x
+base_model: DavidAU/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- zh
+- ja
+- ru
+- ko
+tags:
+- thinking
+- reasoning
+- instruct
+- heretic
+- uncensored
+- abliterated
+- Claude4.5-Opus
+- creative
+- creative writing
+- fiction writing
+- plot generation
+- sub-plot generation
+- story generation
+- scene continue
+- storytelling
+- fiction story
+- science fiction
+- romance
+- all genres
+- story
+- writing
+- vivid prosing
+- vivid writing
+- fiction
+- roleplaying
+- bfloat16
+- role play
+- 128k context
+- llama3.3
+- llama-3
+- llama-3.3
+- unsloth
+- finetune
+- mlx
+- mlx-my-repo
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# alexgusevski/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-fp16
+
+The Model [alexgusevski/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-fp16](https://huggingface.co/alexgusevski/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-fp16) was converted to MLX format from [DavidAU/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning](https://huggingface.co/DavidAU/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning) using mlx-lm version **0.29.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("alexgusevski/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-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)
+```