Instructions to use nightscape/Intern-S2-Mobius-4bit-mlx-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use nightscape/Intern-S2-Mobius-4bit-mlx-mtp 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("nightscape/Intern-S2-Mobius-4bit-mlx-mtp") 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 nightscape/Intern-S2-Mobius-4bit-mlx-mtp with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "nightscape/Intern-S2-Mobius-4bit-mlx-mtp" --prompt "Once upon a time"
- Atomic Chat
| { | |
| "architectures": [ | |
| "InternS2MobiusForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_interns2_mobius.InternS2MobiusConfig", | |
| "AutoModelForCausalLM": "modeling_interns2_mobius.InternS2MobiusForCausalLM", | |
| "AutoModel": "modeling_interns2_mobius.InternS2MobiusModel", | |
| "AutoModelForImageTextToText": "modeling_interns2_mobius.InternS2MobiusForConditionalGeneration", | |
| "AutoModelForMultimodalLM": "modeling_interns2_mobius.InternS2MobiusForConditionalGeneration" | |
| }, | |
| "eos_token_id": [ | |
| 248046, | |
| 248044 | |
| ], | |
| "image_token_id": 248056, | |
| "model_type": "interns2_mobius", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "model.layers.0.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.1.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.2.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.24.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.25.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.26.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.27.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.28.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.29.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.30.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.31.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.32.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.33.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.34.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.35.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.36.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.37.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.38.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.39.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.0.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.1.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.2.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.3.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "mtp.layers.0.mlp.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "mtp.layers.0.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "model.layers.0.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.1.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.2.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.24.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.25.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.26.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.27.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.28.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.29.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.30.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.31.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.32.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.33.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.34.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.35.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.36.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.37.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.38.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.39.mlp.shared_expert_gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.0.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.1.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.2.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.meta_mlp.3.gate": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "text_config": { | |
| "model_type": "interns2_mobius_text", | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 32, | |
| "linear_value_head_dim": 128, | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "moe_intermediate_size": 512, | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "mtp_num_experts": 256, | |
| "mtp_num_experts_per_tok": 8, | |
| "num_attention_heads": 16, | |
| "num_blocks": 4, | |
| "num_experts": 2560, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "router_aux_loss_coef": 0.001, | |
| "shared_expert_intermediate_size": 512, | |
| "use_cache": true, | |
| "vocab_size": 251392, | |
| "mamba_ssm_dtype": "float32", | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "rope_type": "default", | |
| "rope_theta": 10000000, | |
| "partial_rotary_factor": 0.25 | |
| }, | |
| "pad_token_id": null, | |
| "bos_token_id": null, | |
| "tie_word_embeddings": false, | |
| "output_router_logits": false, | |
| "partial_rotary_factor": 0.25 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.2.0", | |
| "video_token_id": 248057, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053 | |
| } |