Instructions to use SakitsunaAI/NexusAISpratova with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SakitsunaAI/NexusAISpratova with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SakitsunaAI/NexusAISpratova", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("SakitsunaAI/NexusAISpratova", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SakitsunaAI/NexusAISpratova with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SakitsunaAI/NexusAISpratova"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakitsunaAI/NexusAISpratova",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SakitsunaAI/NexusAISpratova

SGLang

How to use SakitsunaAI/NexusAISpratova with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SakitsunaAI/NexusAISpratova" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakitsunaAI/NexusAISpratova",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SakitsunaAI/NexusAISpratova" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakitsunaAI/NexusAISpratova",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SakitsunaAI/NexusAISpratova with Docker Model Runner:
```
docker model run hf.co/SakitsunaAI/NexusAISpratova
```

NexusAISpratova / config.json

SakitsunaAI

Upload MiMoForCausalLM

67c0fd7 verified 17 days ago

Raw

History Blame Contribute Delete

2.35 kB

	{
	"architectures": [
	"MiMoForCausalLM"
	],
	"attention_bias": true,
	"attention_dropout": 0.0,
	"auto_map": {
	"AutoConfig": "configuration_mimo.MiMoConfig",
	"AutoModel": "modeling_mimo.MiMoModel",
	"AutoModelForCausalLM": "modeling_mimo.MiMoForCausalLM"
	},
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": null,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 11008,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"max_window_layers": 32,
	"model_type": "mimo",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"num_nextn_predict_layers": 1,
	"pad_token_id": null,
	"quantization_config": {
	"_load_in_4bit": true,
	"_load_in_8bit": false,
	"bnb_4bit_compute_dtype": "bfloat16",
	"bnb_4bit_quant_storage": "uint8",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": true,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": null,
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"rope_theta": 640000,
	"rope_type": "default"
	},
	"sliding_window": null,
	"tie_word_embeddings": false,
	"tokenizer_class": [
	"Qwen2Tokenizer"
	],
	"transformers_version": "5.13.1",
	"use_cache": false,
	"use_mrope": false,
	"use_sliding_window": false,
	"vocab_size": 151680
	}