Instructions to use INCModel/DeepSeek-V4-Pro-MXFP4-LLMC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use INCModel/DeepSeek-V4-Pro-MXFP4-LLMC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="INCModel/DeepSeek-V4-Pro-MXFP4-LLMC")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("INCModel/DeepSeek-V4-Pro-MXFP4-LLMC") model = AutoModelForCausalLM.from_pretrained("INCModel/DeepSeek-V4-Pro-MXFP4-LLMC") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use INCModel/DeepSeek-V4-Pro-MXFP4-LLMC with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "INCModel/DeepSeek-V4-Pro-MXFP4-LLMC" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "INCModel/DeepSeek-V4-Pro-MXFP4-LLMC", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/INCModel/DeepSeek-V4-Pro-MXFP4-LLMC
- SGLang
How to use INCModel/DeepSeek-V4-Pro-MXFP4-LLMC 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 "INCModel/DeepSeek-V4-Pro-MXFP4-LLMC" \ --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": "INCModel/DeepSeek-V4-Pro-MXFP4-LLMC", "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 "INCModel/DeepSeek-V4-Pro-MXFP4-LLMC" \ --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": "INCModel/DeepSeek-V4-Pro-MXFP4-LLMC", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use INCModel/DeepSeek-V4-Pro-MXFP4-LLMC with Docker Model Runner:
docker model run hf.co/INCModel/DeepSeek-V4-Pro-MXFP4-LLMC
| { | |
| "architectures": [ | |
| "DeepseekV4ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 1, | |
| "expert_dtype": "fp4", | |
| "hc_eps": 1e-06, | |
| "hc_mult": 4, | |
| "hc_sinkhorn_iters": 20, | |
| "head_dim": 512, | |
| "hidden_act": "silu", | |
| "hidden_size": 7168, | |
| "index_head_dim": 128, | |
| "index_n_heads": 64, | |
| "index_topk": 1024, | |
| "initializer_range": 0.02, | |
| "max_position_embeddings": 1048576, | |
| "model_type": "deepseek_v4", | |
| "moe_intermediate_size": 3072, | |
| "n_routed_experts": 384, | |
| "n_shared_experts": 1, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 128, | |
| "num_experts_per_tok": 6, | |
| "num_hidden_layers": 61, | |
| "num_hash_layers": 3, | |
| "num_key_value_heads": 1, | |
| "num_nextn_predict_layers": 1, | |
| "o_groups": 16, | |
| "o_lora_rank": 1024, | |
| "q_lora_rank": 1536, | |
| "qk_rope_head_dim": 64, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "num_bits": 4, | |
| "type": "float", | |
| "symmetric": true, | |
| "group_size": 32, | |
| "strategy": "group", | |
| "block_structure": null, | |
| "dynamic": false, | |
| "actorder": null, | |
| "scale_dtype": "torch.uint8", | |
| "zp_dtype": null, | |
| "observer": "memoryless_minmax", | |
| "observer_kwargs": {} | |
| }, | |
| "input_activations": { | |
| "num_bits": 4, | |
| "type": "float", | |
| "symmetric": true, | |
| "group_size": 32, | |
| "strategy": "group", | |
| "block_structure": null, | |
| "dynamic": true, | |
| "actorder": null, | |
| "scale_dtype": "torch.uint8", | |
| "zp_dtype": null, | |
| "observer": null, | |
| "observer_kwargs": {} | |
| }, | |
| "output_activations": null, | |
| "format": null | |
| } | |
| }, | |
| "quant_method": "compressed-tensors", | |
| "kv_cache_scheme": null, | |
| "format": "mxfp4-pack-quantized", | |
| "quantization_status": "compressed", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "embed", | |
| "layers.0.attn.compressor.wgate", | |
| "layers.0.attn.compressor.wkv", | |
| "layers.0.ffn.gate", | |
| "layers.1.attn.compressor.wgate", | |
| "layers.1.attn.compressor.wkv", | |
| "layers.1.ffn.gate", | |
| "layers.2.attn.compressor.wgate", | |
| "layers.2.attn.compressor.wkv", | |
| "layers.2.attn.indexer.compressor.wgate", | |
| "layers.2.attn.indexer.compressor.wkv", | |
| "layers.2.attn.indexer.weights_proj", | |
| "layers.2.ffn.gate", | |
| "layers.3.attn.compressor.wgate", | |
| "layers.3.attn.compressor.wkv", | |
| "layers.3.ffn.gate", | |
| "layers.4.attn.compressor.wgate", | |
| "layers.4.attn.compressor.wkv", | |
| "layers.4.attn.indexer.compressor.wgate", | |
| "layers.4.attn.indexer.compressor.wkv", | |
| "layers.4.attn.indexer.weights_proj", | |
| "layers.4.ffn.gate", | |
| "layers.5.attn.compressor.wgate", | |
| "layers.5.attn.compressor.wkv", | |
| "layers.5.ffn.gate", | |
| "layers.6.attn.compressor.wgate", | |
| "layers.6.attn.compressor.wkv", | |
| "layers.6.attn.indexer.compressor.wgate", | |
| "layers.6.attn.indexer.compressor.wkv", | |
| "layers.6.attn.indexer.weights_proj", | |
| "layers.6.ffn.gate", | |
| "layers.7.attn.compressor.wgate", | |
| "layers.7.attn.compressor.wkv", | |
| "layers.7.ffn.gate", | |
| "layers.8.attn.wo_b", | |
| "layers.8.attn.compressor.wgate", | |
| "layers.8.attn.compressor.wkv", | |
| "layers.8.attn.indexer.compressor.wgate", | |
| "layers.8.attn.indexer.compressor.wkv", | |
| "layers.8.attn.indexer.weights_proj", | |
| "layers.8.ffn.gate", | |
| "layers.9.attn.compressor.wgate", | |
| "layers.9.attn.compressor.wkv", | |
| "layers.9.ffn.gate", | |
| "layers.10.attn.compressor.wgate", | |
| "layers.10.attn.compressor.wkv", | |
| "layers.10.attn.indexer.compressor.wgate", | |
| "layers.10.attn.indexer.compressor.wkv", | |
| "layers.10.attn.indexer.weights_proj", | |
| "layers.10.ffn.gate", | |
| "layers.11.attn.compressor.wgate", | |
| "layers.11.attn.compressor.wkv", | |
| "layers.11.ffn.gate", | |
| "layers.12.attn.compressor.wgate", | |
| "layers.12.attn.compressor.wkv", | |
| "layers.12.attn.indexer.compressor.wgate", | |
| "layers.12.attn.indexer.compressor.wkv", | |
| "layers.12.attn.indexer.weights_proj", | |
| "layers.12.ffn.gate", | |
| "layers.13.attn.compressor.wgate", | |
| "layers.13.attn.compressor.wkv", | |
| "layers.13.ffn.gate", | |
| "layers.14.attn.compressor.wgate", | |
| "layers.14.attn.compressor.wkv", | |
| "layers.14.attn.indexer.compressor.wgate", | |
| "layers.14.attn.indexer.compressor.wkv", | |
| "layers.14.attn.indexer.weights_proj", | |
| "layers.14.ffn.gate", | |
| "layers.15.attn.compressor.wgate", | |
| "layers.15.attn.compressor.wkv", | |
| "layers.15.ffn.gate", | |
| "layers.16.attn.compressor.wgate", | |
| "layers.16.attn.compressor.wkv", | |
| "layers.16.attn.indexer.compressor.wgate", | |
| "layers.16.attn.indexer.compressor.wkv", | |
| "layers.16.attn.indexer.weights_proj", | |
| "layers.16.ffn.gate", | |
| "layers.17.attn.compressor.wgate", | |
| "layers.17.attn.compressor.wkv", | |
| "layers.17.ffn.gate", | |
| "layers.18.attn.compressor.wgate", | |
| "layers.18.attn.compressor.wkv", | |
| "layers.18.attn.indexer.compressor.wgate", | |
| "layers.18.attn.indexer.compressor.wkv", | |
| "layers.18.attn.indexer.weights_proj", | |
| "layers.18.ffn.gate", | |
| "layers.19.attn.compressor.wgate", | |
| "layers.19.attn.compressor.wkv", | |
| "layers.19.ffn.gate", | |
| "layers.20.attn.compressor.wgate", | |
| "layers.20.attn.compressor.wkv", | |
| "layers.20.attn.indexer.compressor.wgate", | |
| "layers.20.attn.indexer.compressor.wkv", | |
| "layers.20.attn.indexer.weights_proj", | |
| "layers.20.ffn.gate", | |
| "layers.21.attn.compressor.wgate", | |
| "layers.21.attn.compressor.wkv", | |
| "layers.21.ffn.gate", | |
| "layers.22.attn.compressor.wgate", | |
| "layers.22.attn.compressor.wkv", | |
| "layers.22.attn.indexer.compressor.wgate", | |
| "layers.22.attn.indexer.compressor.wkv", | |
| "layers.22.attn.indexer.weights_proj", | |
| "layers.22.ffn.gate", | |
| "layers.23.attn.compressor.wgate", | |
| "layers.23.attn.compressor.wkv", | |
| "layers.23.ffn.gate", | |
| "layers.24.attn.compressor.wgate", | |
| "layers.24.attn.compressor.wkv", | |
| "layers.24.attn.indexer.compressor.wgate", | |
| "layers.24.attn.indexer.compressor.wkv", | |
| "layers.24.attn.indexer.weights_proj", | |
| "layers.24.ffn.gate", | |
| "layers.25.attn.compressor.wgate", | |
| "layers.25.attn.compressor.wkv", | |
| "layers.25.ffn.gate", | |
| "layers.26.attn.compressor.wgate", | |
| "layers.26.attn.compressor.wkv", | |
| "layers.26.attn.indexer.compressor.wgate", | |
| "layers.26.attn.indexer.compressor.wkv", | |
| "layers.26.attn.indexer.weights_proj", | |
| "layers.26.ffn.gate", | |
| "layers.27.attn.compressor.wgate", | |
| "layers.27.attn.compressor.wkv", | |
| "layers.27.ffn.gate", | |
| "layers.28.attn.compressor.wgate", | |
| "layers.28.attn.compressor.wkv", | |
| "layers.28.attn.indexer.compressor.wgate", | |
| "layers.28.attn.indexer.compressor.wkv", | |
| "layers.28.attn.indexer.weights_proj", | |
| "layers.28.ffn.gate", | |
| "layers.29.attn.compressor.wgate", | |
| "layers.29.attn.compressor.wkv", | |
| "layers.29.ffn.gate", | |
| "layers.30.attn.compressor.wgate", | |
| "layers.30.attn.compressor.wkv", | |
| "layers.30.attn.indexer.compressor.wgate", | |
| "layers.30.attn.indexer.compressor.wkv", | |
| "layers.30.attn.indexer.weights_proj", | |
| "layers.30.ffn.gate", | |
| "layers.31.attn.compressor.wgate", | |
| "layers.31.attn.compressor.wkv", | |
| "layers.31.ffn.gate", | |
| "layers.32.attn.compressor.wgate", | |
| "layers.32.attn.compressor.wkv", | |
| "layers.32.attn.indexer.compressor.wgate", | |
| "layers.32.attn.indexer.compressor.wkv", | |
| "layers.32.attn.indexer.weights_proj", | |
| "layers.32.ffn.gate", | |
| "layers.33.attn.compressor.wgate", | |
| "layers.33.attn.compressor.wkv", | |
| "layers.33.ffn.gate", | |
| "layers.34.attn.compressor.wgate", | |
| "layers.34.attn.compressor.wkv", | |
| "layers.34.attn.indexer.compressor.wgate", | |
| "layers.34.attn.indexer.compressor.wkv", | |
| "layers.34.attn.indexer.weights_proj", | |
| "layers.34.ffn.gate", | |
| "layers.35.attn.compressor.wgate", | |
| "layers.35.attn.compressor.wkv", | |
| "layers.35.ffn.gate", | |
| "layers.36.attn.compressor.wgate", | |
| "layers.36.attn.compressor.wkv", | |
| "layers.36.attn.indexer.compressor.wgate", | |
| "layers.36.attn.indexer.compressor.wkv", | |
| "layers.36.attn.indexer.weights_proj", | |
| "layers.36.ffn.gate", | |
| "layers.37.attn.compressor.wgate", | |
| "layers.37.attn.compressor.wkv", | |
| "layers.37.ffn.gate", | |
| "layers.38.attn.compressor.wgate", | |
| "layers.38.attn.compressor.wkv", | |
| "layers.38.attn.indexer.compressor.wgate", | |
| "layers.38.attn.indexer.compressor.wkv", | |
| "layers.38.attn.indexer.weights_proj", | |
| "layers.38.ffn.gate", | |
| "layers.39.attn.compressor.wgate", | |
| "layers.39.attn.compressor.wkv", | |
| "layers.39.ffn.gate", | |
| "layers.40.attn.compressor.wgate", | |
| "layers.40.attn.compressor.wkv", | |
| "layers.40.attn.indexer.compressor.wgate", | |
| "layers.40.attn.indexer.compressor.wkv", | |
| "layers.40.attn.indexer.weights_proj", | |
| "layers.40.ffn.gate", | |
| "layers.41.attn.compressor.wgate", | |
| "layers.41.attn.compressor.wkv", | |
| "layers.41.ffn.gate", | |
| "layers.42.attn.compressor.wgate", | |
| "layers.42.attn.compressor.wkv", | |
| "layers.42.attn.indexer.compressor.wgate", | |
| "layers.42.attn.indexer.compressor.wkv", | |
| "layers.42.attn.indexer.weights_proj", | |
| "layers.42.ffn.gate", | |
| "layers.43.attn.compressor.wgate", | |
| "layers.43.attn.compressor.wkv", | |
| "layers.43.ffn.gate", | |
| "layers.44.attn.compressor.wgate", | |
| "layers.44.attn.compressor.wkv", | |
| "layers.44.attn.indexer.compressor.wgate", | |
| "layers.44.attn.indexer.compressor.wkv", | |
| "layers.44.attn.indexer.weights_proj", | |
| "layers.44.ffn.gate", | |
| "layers.45.attn.compressor.wgate", | |
| "layers.45.attn.compressor.wkv", | |
| "layers.45.ffn.gate", | |
| "layers.46.attn.compressor.wgate", | |
| "layers.46.attn.compressor.wkv", | |
| "layers.46.attn.indexer.compressor.wgate", | |
| "layers.46.attn.indexer.compressor.wkv", | |
| "layers.46.attn.indexer.weights_proj", | |
| "layers.46.ffn.gate", | |
| "layers.47.attn.compressor.wgate", | |
| "layers.47.attn.compressor.wkv", | |
| "layers.47.ffn.gate", | |
| "layers.48.attn.compressor.wgate", | |
| "layers.48.attn.compressor.wkv", | |
| "layers.48.attn.indexer.compressor.wgate", | |
| "layers.48.attn.indexer.compressor.wkv", | |
| "layers.48.attn.indexer.weights_proj", | |
| "layers.48.ffn.gate", | |
| "layers.49.attn.compressor.wgate", | |
| "layers.49.attn.compressor.wkv", | |
| "layers.49.ffn.gate", | |
| "layers.50.attn.compressor.wgate", | |
| "layers.50.attn.compressor.wkv", | |
| "layers.50.attn.indexer.compressor.wgate", | |
| "layers.50.attn.indexer.compressor.wkv", | |
| "layers.50.attn.indexer.weights_proj", | |
| "layers.50.ffn.gate", | |
| "layers.51.attn.compressor.wgate", | |
| "layers.51.attn.compressor.wkv", | |
| "layers.51.ffn.gate", | |
| "layers.52.attn.compressor.wgate", | |
| "layers.52.attn.compressor.wkv", | |
| "layers.52.attn.indexer.compressor.wgate", | |
| "layers.52.attn.indexer.compressor.wkv", | |
| "layers.52.attn.indexer.weights_proj", | |
| "layers.52.ffn.gate", | |
| "layers.53.attn.compressor.wgate", | |
| "layers.53.attn.compressor.wkv", | |
| "layers.53.ffn.gate", | |
| "layers.54.attn.compressor.wgate", | |
| "layers.54.attn.compressor.wkv", | |
| "layers.54.attn.indexer.compressor.wgate", | |
| "layers.54.attn.indexer.compressor.wkv", | |
| "layers.54.attn.indexer.weights_proj", | |
| "layers.54.ffn.gate", | |
| "layers.55.attn.compressor.wgate", | |
| "layers.55.attn.compressor.wkv", | |
| "layers.55.ffn.gate", | |
| "layers.56.attn.compressor.wgate", | |
| "layers.56.attn.compressor.wkv", | |
| "layers.56.attn.indexer.compressor.wgate", | |
| "layers.56.attn.indexer.compressor.wkv", | |
| "layers.56.attn.indexer.weights_proj", | |
| "layers.56.ffn.gate", | |
| "layers.57.attn.compressor.wgate", | |
| "layers.57.attn.compressor.wkv", | |
| "layers.57.ffn.gate", | |
| "layers.58.attn.compressor.wgate", | |
| "layers.58.attn.compressor.wkv", | |
| "layers.58.attn.indexer.compressor.wgate", | |
| "layers.58.attn.indexer.compressor.wkv", | |
| "layers.58.attn.indexer.weights_proj", | |
| "layers.58.ffn.gate", | |
| "layers.59.attn.compressor.wgate", | |
| "layers.59.attn.compressor.wkv", | |
| "layers.59.ffn.gate", | |
| "layers.60.attn.compressor.wgate", | |
| "layers.60.attn.compressor.wkv", | |
| "layers.60.attn.indexer.compressor.wgate", | |
| "layers.60.attn.indexer.compressor.wkv", | |
| "layers.60.attn.indexer.weights_proj", | |
| "layers.60.ffn.gate", | |
| "head", | |
| "mtp.0.ffn.gate" | |
| ], | |
| "provider": "auto-round" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "beta_fast": 32, | |
| "beta_slow": 1, | |
| "factor": 16, | |
| "original_max_position_embeddings": 65536, | |
| "type": "yarn" | |
| }, | |
| "rope_theta": 10000, | |
| "routed_scaling_factor": 2.5, | |
| "scoring_func": "sqrtsoftplus", | |
| "sliding_window": 128, | |
| "swiglu_limit": 10.0, | |
| "tie_word_embeddings": false, | |
| "topk_method": "noaux_tc", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.57.1", | |
| "use_cache": true, | |
| "vocab_size": 129280, | |
| "compress_rope_theta": 160000, | |
| "compress_ratios": [ | |
| 128, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 128, | |
| 4, | |
| 0 | |
| ] | |
| } |