Instructions to use autotrust/DeepSeek-V4-Flash-DSpark-4E with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use autotrust/DeepSeek-V4-Flash-DSpark-4E with Transformers:

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

pipe = pipeline("text-generation", model="autotrust/DeepSeek-V4-Flash-DSpark-4E")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("autotrust/DeepSeek-V4-Flash-DSpark-4E")
model = AutoModelForCausalLM.from_pretrained("autotrust/DeepSeek-V4-Flash-DSpark-4E", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use autotrust/DeepSeek-V4-Flash-DSpark-4E with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "autotrust/DeepSeek-V4-Flash-DSpark-4E"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "autotrust/DeepSeek-V4-Flash-DSpark-4E",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/autotrust/DeepSeek-V4-Flash-DSpark-4E

SGLang

How to use autotrust/DeepSeek-V4-Flash-DSpark-4E 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 "autotrust/DeepSeek-V4-Flash-DSpark-4E" \
    --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": "autotrust/DeepSeek-V4-Flash-DSpark-4E",
		"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 "autotrust/DeepSeek-V4-Flash-DSpark-4E" \
        --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": "autotrust/DeepSeek-V4-Flash-DSpark-4E",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use autotrust/DeepSeek-V4-Flash-DSpark-4E with Docker Model Runner:
```
docker model run hf.co/autotrust/DeepSeek-V4-Flash-DSpark-4E
```

DeepSeek-V4-Flash-DSpark-4E / MMLU_PRO_EVAL.md

cloudyu

Upload folder using huggingface_hub

c7e88d7 verified 24 days ago

preview code

Raw

History Blame Contribute Delete

3.3 kB

MMLU-Pro Evaluation: DeepSeek-V4-Flash-DSpark (top_k=4 vs top_k=6)

Setup

All evaluations use the following configuration:

Inference mode: chat (no <think> prefix)
max_tokens: 20 (single-letter answer extraction)
vLLM version: 0.23.0
GPU: single NVIDIA B300 SXM6 (sm_103a, 275 GB VRAM)
DeepGEMM: enabled (VLLM_USE_DEEP_GEMM unset, all 2562 kernels JIT-compiled at warmup)
KV cache dtype: fp8
Dataset: MMLU-Pro (12,032 questions, A–J categories)
Backend: flashinfer::trtllm_fp4_block_scale_moe for MXFP4 MoE, DeepGemmFp8BlockScaledMM for FP8 linear

Model Configuration Detail

Both runs use the same checkpoint files. The only difference is the num_experts_per_tok parameter and how the tid2eid (hash-based expert routing table) weight tensors are handled:

Setting	`num_experts_per_tok`	`tid2eid` handling
top_k=4	4	Sliced from `[vocab_size, 6]` → `[vocab_size, 4]` (first 4 columns retained)
top_k=6	6	Loaded as-is from checkpoint (`[vocab_size, 6]`)

The checkpoint stores tid2eid weights with shape [129280, 6] for the first 3 hash-based MoE routing layers. When num_experts_per_tok=4, the model parameter shape is [129280, 4]; the weight is sliced to match.

Results

Overall Accuracy

Configuration	Accuracy	Correct / Total	Generation Time	Engine Init Time
top_k=4	42.30%	5,090 / 12,032	73.0 s	167.9 s
top_k=6	39.27%	4,725 / 12,032	89.0 s	186.9 s
Δ (4−6)	+3.03%	+365	−16.0 s	−19.0 s

Using num_experts_per_tok=4 (with tid2eid slicing) gives a +3.03 percentage point lift over num_experts_per_tok=6, with faster generation and engine initialization.

Per-Category Breakdown (top_k=4)

Only the top_k=4 run recorded per-category metrics:

Category	Accuracy
biology	492/717 = 68.6%
business	325/789 = 41.2%
chemistry	214/1132 = 18.9%
computer science	194/410 = 47.3%
economics	557/844 = 66.0%
engineering	262/969 = 27.0%
health	483/818 = 59.0%
history	191/381 = 50.1%
law	369/1101 = 33.5%
math	393/1351 = 29.1%
other	507/924 = 54.9%
philosophy	263/499 = 52.7%
physics	291/1299 = 22.4%
psychology	549/798 = 68.8%

Comparison: DSpark vs 4E (both top_k=4)

Model	Accuracy	Generation Time
DeepSeek-V4-Flash-DSpark	42.30%	73.0 s
DeepSeek-V4-Flash-4E	41.75%	122.0 s
Δ (DSpark−4E)	+0.55%	−49.0 s

DSpark at top_k=4 slightly outperforms the 4E reference model (+0.55%) while generating answers 40% faster (73 s vs 122 s).

Key Takeaway

num_experts_per_tok=4 is the correct setting for DeepSeek-V4-Flash-DSpark on MMLU-Pro. Despite the checkpoint storing 6-column tid2eid weights (originally for top_k=6 evaluation), forcing top_k=6 degrades accuracy by ~3 percentage points. The canonical top_k=4 with sliced weight loading achieves the best accuracy (42.30%) and ties or exceeds the comparable 4E model.