Instructions to use ToPo-ToPo/DeepSeek-V4-Flash-MTP-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use ToPo-ToPo/DeepSeek-V4-Flash-MTP-bf16 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("ToPo-ToPo/DeepSeek-V4-Flash-MTP-bf16") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use ToPo-ToPo/DeepSeek-V4-Flash-MTP-bf16 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "ToPo-ToPo/DeepSeek-V4-Flash-MTP-bf16" --prompt "Once upon a time"
File size: 170 Bytes
76d99ad | 1 2 3 4 5 6 7 8 9 10 | {
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": 1,
"do_sample": true,
"temperature": 1.0,
"top_p": 1.0,
"transformers_version": "4.46.3"
}
|