Instructions to use ArchiveStudio/MiniCPM5-2B-DSpark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArchiveStudio/MiniCPM5-2B-DSpark with Transformers:

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

pipe = pipeline("text-generation", model="ArchiveStudio/MiniCPM5-2B-DSpark", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("ArchiveStudio/MiniCPM5-2B-DSpark", trust_remote_code=True)
model = AutoModel.from_pretrained("ArchiveStudio/MiniCPM5-2B-DSpark", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArchiveStudio/MiniCPM5-2B-DSpark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArchiveStudio/MiniCPM5-2B-DSpark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchiveStudio/MiniCPM5-2B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArchiveStudio/MiniCPM5-2B-DSpark

SGLang

How to use ArchiveStudio/MiniCPM5-2B-DSpark 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 "ArchiveStudio/MiniCPM5-2B-DSpark" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchiveStudio/MiniCPM5-2B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ArchiveStudio/MiniCPM5-2B-DSpark" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArchiveStudio/MiniCPM5-2B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArchiveStudio/MiniCPM5-2B-DSpark with Docker Model Runner:
```
docker model run hf.co/ArchiveStudio/MiniCPM5-2B-DSpark
```

MiniCPM5-2B-DSpark

File size: 1,414 Bytes

48ad621

{
  "architectures": [
    "Qwen3DSparkModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoModel": "dspark.DSparkDraftModel"
  },
  "block_size": 7,
  "bos_token_id": 0,
  "draft_vocab_size": 130560,
  "dtype": "bfloat16",
  "eos_token_id": [
    1,
    130073
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 5,
  "mlp_bias": false,
  "model_type": "qwen3",
  "num_attention_heads": 16,
  "num_hidden_layers": 5,
  "num_key_value_heads": 2,
  "num_target_layers": 42,
  "pad_token_id": 1,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 5000000,
    "rope_type": "default"
  },
  "sliding_window": null,
  "tie_word_embeddings": false,
  "transformers_version": "5.12.1",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 130560,
  "attention_mode": "gqa",
  "confidence_head_alpha": 1.0,
  "confidence_head_with_markov": true,
  "enable_confidence_head": true,
  "markov_head_type": "vanilla",
  "markov_rank": 256,
  "mask_token_id": 75982,
  "projector_type": "dspark",
  "target_layer_ids": [
    1,
    10,
    20,
    30,
    39
  ]
}