introvoyz041's picture
Upload README.md with huggingface_hub
407fab6 verified
metadata
license: apache-2.0
language:
  - en
  - code
library_name: transformers
tags:
  - causal-lm
  - moe
  - mixture-of-experts
  - qwen
  - distillation
  - svd
  - lora-merged
  - code-generation
  - mlx
  - mlx-my-repo
  - mlx
  - mlx-my-repo
base_model: YOYO-AI/Qwen3-Coder-30B-A3B-Instruct-480B-Distill-V2-Fp32-mlx-fp16

introvoyz041/Qwen3-Coder-30B-A3B-Instruct-480B-Distill-V2-Fp32-mlx-fp16-mlx-4Bit

The Model introvoyz041/Qwen3-Coder-30B-A3B-Instruct-480B-Distill-V2-Fp32-mlx-fp16-mlx-4Bit was converted to MLX format from YOYO-AI/Qwen3-Coder-30B-A3B-Instruct-480B-Distill-V2-Fp32-mlx-fp16 using mlx-lm version 0.28.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("introvoyz041/Qwen3-Coder-30B-A3B-Instruct-480B-Distill-V2-Fp32-mlx-fp16-mlx-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)