Instructions to use bighouse520/DeepSeek-V4-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bighouse520/DeepSeek-V4-Flash with Transformers:

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

pipe = pipeline("text-generation", model="bighouse520/DeepSeek-V4-Flash")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bighouse520/DeepSeek-V4-Flash")
model = AutoModelForCausalLM.from_pretrained("bighouse520/DeepSeek-V4-Flash")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bighouse520/DeepSeek-V4-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bighouse520/DeepSeek-V4-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bighouse520/DeepSeek-V4-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bighouse520/DeepSeek-V4-Flash

SGLang

How to use bighouse520/DeepSeek-V4-Flash 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 "bighouse520/DeepSeek-V4-Flash" \
    --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": "bighouse520/DeepSeek-V4-Flash",
		"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 "bighouse520/DeepSeek-V4-Flash" \
        --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": "bighouse520/DeepSeek-V4-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bighouse520/DeepSeek-V4-Flash with Docker Model Runner:
```
docker model run hf.co/bighouse520/DeepSeek-V4-Flash
```

DeepSeek-V4-Flash / config.json

bighouse520

Duplicate from deepseek-ai/DeepSeek-V4-Flash

fa1eae1 12 days ago

raw

history blame contribute delete

1.72 kB

	{
	"architectures": [
	"DeepseekV4ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 0,
	"eos_token_id": 1,
	"hc_eps": 1e-06,
	"hc_mult": 4,
	"hc_sinkhorn_iters": 20,
	"head_dim": 512,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"index_head_dim": 128,
	"index_n_heads": 64,
	"index_topk": 512,
	"initializer_range": 0.02,
	"max_position_embeddings": 1048576,
	"model_type": "deepseek_v4",
	"moe_intermediate_size": 2048,
	"n_routed_experts": 256,
	"n_shared_experts": 1,
	"norm_topk_prob": true,
	"num_attention_heads": 64,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 43,
	"num_hash_layers": 3,
	"num_key_value_heads": 1,
	"num_nextn_predict_layers": 1,
	"o_groups": 8,
	"o_lora_rank": 1024,
	"q_lora_rank": 1024,
	"qk_rope_head_dim": 64,
	"quantization_config": {
	"activation_scheme": "dynamic",
	"fmt": "e4m3",
	"quant_method": "fp8",
	"scale_fmt": "ue8m0",
	"weight_block_size": [
	128,
	128
	]
	},
	"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": 1.5,
	"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": [0, 0, 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]
	}