metadata
license: gpl-3.0
datasets:
- MinervaAI/Aesir-Preview
- Gryphe/Sonnet3.5-Charcard-Roleplay
base_model: Orion-zhen/Meissa-Qwen2.5-14B-Instruct
tags:
- mlx
Fmuaddib/Meissa-Qwen2.5-14B-Instruct-mlx-fp16
The Model Fmuaddib/Meissa-Qwen2.5-14B-Instruct-mlx-fp16 was converted to MLX format from Orion-zhen/Meissa-Qwen2.5-14B-Instruct using mlx-lm version 0.22.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Fmuaddib/Meissa-Qwen2.5-14B-Instruct-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)