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

Libraries

How to use deepseek-ai/DeepSeek-V4-Flash with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/DeepSeek-V4-Flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-ai/DeepSeek-V4-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4-Flash

SGLang

How to use deepseek-ai/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 "deepseek-ai/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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash",
		"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 "deepseek-ai/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/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4-Flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Add community evaluation results for GPQA, MMLU-PRO, SWE-BENCH_VERIFIED, HLE, TERMINAL-BENCH-2.0

#11

by nielsr HF Staff - opened 30 days ago

base: refs/heads/main

←

from: refs/pr/11

Discussion Files changed

+35

-0

YAML Metadata Error:Invalid content in Eval Result file .eval_results/hle.yaml

Check out the documentation for more information.

Show details

Task ID "hle" does not match any task in dataset "cais/hle". Available: none

Files changed (5) hide show

.eval_results/gpqa.yaml +7 -0
.eval_results/hle.yaml +7 -0
.eval_results/mmlu-pro.yaml +7 -0
.eval_results/swe-bench_verified.yaml +7 -0
.eval_results/terminal-bench-2.0.yaml +7 -0

.eval_results/gpqa.yaml ADDED Viewed

	@@ -0,0 +1,7 @@

+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 88.1
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
+    name: Model Card

.eval_results/hle.yaml ADDED Viewed

	@@ -0,0 +1,7 @@

+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 34.8
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
+    name: Model Card

.eval_results/mmlu-pro.yaml ADDED Viewed

	@@ -0,0 +1,7 @@

+- dataset:
+    id: TIGER-Lab/MMLU-Pro
+    task_id: mmlu_pro
+  value: 86.4
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
+    name: Model Card

.eval_results/swe-bench_verified.yaml ADDED Viewed

	@@ -0,0 +1,7 @@

+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 79
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
+    name: Model Card

.eval_results/terminal-bench-2.0.yaml ADDED Viewed

	@@ -0,0 +1,7 @@

+- dataset:
+    id: harborframework/terminal-bench-2.0
+    task_id: terminalbench_2
+  value: 56.9
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
+    name: Model Card