Text Generation
MLX
Safetensors
deepseek_v4
jang
jangtq
jangtq2
jangtq-prestack
mxtq
deepseek
deepseek-v4
deepseek-v4-flash
Mixture of Experts
mla
hash-layers
mtp
apple-silicon
osaurus
Instructions to use OsaurusAI/DeepSeek-V4-Flash-JANGTQ2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OsaurusAI/DeepSeek-V4-Flash-JANGTQ2 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("OsaurusAI/DeepSeek-V4-Flash-JANGTQ2") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
- MLX LM
How to use OsaurusAI/DeepSeek-V4-Flash-JANGTQ2 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "OsaurusAI/DeepSeek-V4-Flash-JANGTQ2" --prompt "Once upon a time"
File size: 191 Bytes
9e6f5b7 | 1 2 3 4 5 6 7 8 9 10 11 12 | {
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": [
1,
128803
],
"do_sample": true,
"temperature": 1.0,
"top_p": 1.0,
"transformers_version": "4.46.3"
} |