Text Generation
MLX
Safetensors
English
Chinese
Mixture of Experts
mixture-of-experts
minimax_m2
quantized
apple-silicon
turboquant
jangtq
jangtq2
reap
Instructions to use OsaurusAI/MiniMax-M2.7-Small-JANGTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OsaurusAI/MiniMax-M2.7-Small-JANGTQ 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/MiniMax-M2.7-Small-JANGTQ") 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 OsaurusAI/MiniMax-M2.7-Small-JANGTQ 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/MiniMax-M2.7-Small-JANGTQ" --prompt "Once upon a time"
| { | |
| "weight_format": "mxtq", | |
| "profile": "JANGTQ2", | |
| "mxtq_seed": 42, | |
| "source_model": "JANGQ-AI/MiniMax-M2.7-Small", | |
| "source_config": { | |
| "n_routed_experts": 154, | |
| "num_hidden_layers": 62 | |
| }, | |
| "mxtq_bits": { | |
| "routed_expert": 2, | |
| "attention": 8, | |
| "dense_mlp": 8, | |
| "embed_tokens": 8, | |
| "lm_head": 8, | |
| "norms_router": 16 | |
| } | |
| } |