Model: alexgusevski/Llama3.3-8B-Instruct-Thinking-Heretic-Uncensored-Claude-4.5-Opus-High-Reasoning-mlx-fp16 Source: Original Platform
82 lines
1.9 KiB
Markdown
82 lines
1.9 KiB
Markdown
---
|
|
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)
|
|
```
|