license: mit | |
base_model: open-neo/Kyro-n1-14B | |
library_name: transformers | |
language: | |
- en | |
- zh | |
- fr | |
- es | |
- pt | |
- de | |
- it | |
- ru | |
- ja | |
- ko | |
- vi | |
- th | |
- ar | |
- fa | |
- he | |
- tr | |
- cs | |
- pl | |
- hi | |
- bn | |
- ur | |
- id | |
- ms | |
- lo | |
- my | |
- ceb | |
- km | |
- tl | |
- nl | |
tags: | |
- trl | |
- Reasoning | |
- open-llm | |
- synthetic-data | |
- Deepseek-R1 | |
- Qwen2.5 | |
- fine-tune | |
- unsloth | |
- Conversational | |
- Agentic | |
- mlx | |
- mlx-my-repo | |
# KYUNGYONG/Kyro-n1-14B-4bit | |
The Model [KYUNGYONG/Kyro-n1-14B-4bit](https://huggingface.co/KYUNGYONG/Kyro-n1-14B-4bit) was converted to MLX format from [open-neo/Kyro-n1-14B](https://huggingface.co/open-neo/Kyro-n1-14B) using mlx-lm version **0.21.5**. | |
## Use with mlx | |
```bash | |
pip install mlx-lm | |
``` | |
```python | |
from mlx_lm import load, generate | |
model, tokenizer = load("KYUNGYONG/Kyro-n1-14B-4bit") | |
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) | |
``` | |