Instructions to use tiny-random/deepseek-v4.1-flash-1017 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/deepseek-v4.1-flash-1017 with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/deepseek-v4.1-flash-1017")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tiny-random/deepseek-v4.1-flash-1017", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/deepseek-v4.1-flash-1017 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/deepseek-v4.1-flash-1017"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/deepseek-v4.1-flash-1017",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tiny-random/deepseek-v4.1-flash-1017

SGLang

How to use tiny-random/deepseek-v4.1-flash-1017 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 "tiny-random/deepseek-v4.1-flash-1017" \
    --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": "tiny-random/deepseek-v4.1-flash-1017",
		"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 "tiny-random/deepseek-v4.1-flash-1017" \
        --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": "tiny-random/deepseek-v4.1-flash-1017",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tiny-random/deepseek-v4.1-flash-1017 with Docker Model Runner:
```
docker model run hf.co/tiny-random/deepseek-v4.1-flash-1017
```

yujiepan commited on 12 days ago

Commit

f39cf5c

verified ·

1 Parent(s): de51c19

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

.meta.json +7 -6
README.md +5 -4

.meta.json CHANGED Viewed

@@ -1,11 +1,12 @@
 {
-  "Pillow": "12.3.0",
-  "flashinfer-python": "0.6.15.post1",
-  "huggingface_hub": "1.27.0",
-  "numpy": "2.5.2",
   "safetensors": "0.8.0",
   "sympy": "1.14.0",
   "tilelang": "0.1.12",
-  "torch": "2.13.0+cu126",
-  "transformers": "5.15.0.dev0"
 }

 {
+  "Pillow": "12.2.0",
+  "flashinfer-python": "0.7.2",
+  "huggingface_hub": "1.33.0",
+  "numpy": "2.3.5",
   "safetensors": "0.8.0",
+  "sglang": "0.5.23.dev384+g9ab74b851",
   "sympy": "1.14.0",
   "tilelang": "0.1.12",
+  "torch": "2.14.1",
+  "transformers": "5.19.0"
 }

README.md CHANGED Viewed

@@ -46,8 +46,9 @@ Note:
     expert counts, vocabulary rows, and 32-wide quantization blocks divide cleanly by 2.
     The online example enables the embedded three-stage DSpark/MTP draft explicitly.
-  - TP=2 with DSpark/MTP and CUDA Graph was validated on two NVIDIA H20 GPUs
-    using the versions listed under Test environment.
 | File path | Size |
 |------|------|
@@ -61,7 +62,7 @@ Note:
 ```bash
 # Requires an SGLang preview/main build with DeepSeek-V4.1 support.
 # Runs the target model and its embedded three-stage DSpark/MTP draft with TP=2.
-model_id=yujiepan/deepseek-v4.1-flash-1017-tiny-random
 sglang serve \
   --model-path $model_id \
   --trust-remote-code \
@@ -95,7 +96,7 @@ from safetensors.torch import save_file
 from transformers import AutoTokenizer
 source_model_id = "deepseek-ai/DeepSeek-V4.1-Flash-1017"
-save_folder = "/tmp/yujiepan/deepseek-v41-flash-1017-tiny-random"
 source_revision = "1bae0e1088993b9b82de08f59de5be5a34e42170"
 # DeepSeek-V4.1-Flash-1017 is a multimodal (vision + text) MoE model. The released checkpoint uses the
 # inference-stack tensor naming (see the repo's inference/model.py), not HF-transformers naming, so

     expert counts, vocabulary rows, and 32-wide quantization blocks divide cleanly by 2.
     The online example enables the embedded three-stage DSpark/MTP draft explicitly.
+  - TP=2 inference with DSpark/MTP and CUDA Graph was validated for both
+    text-only and image-plus-text requests on two NVIDIA H20 GPUs, using the
+    versions listed under Test environment.
 | File path | Size |
 |------|------|
 ```bash
 # Requires an SGLang preview/main build with DeepSeek-V4.1 support.
 # Runs the target model and its embedded three-stage DSpark/MTP draft with TP=2.
+model_id=tiny-random/deepseek-v4.1-flash-1017
 sglang serve \
   --model-path $model_id \
   --trust-remote-code \
 from transformers import AutoTokenizer
 source_model_id = "deepseek-ai/DeepSeek-V4.1-Flash-1017"
+save_folder = "/tmp/tiny-random/deepseek-v41-flash-1017"
 source_revision = "1bae0e1088993b9b82de08f59de5be5a34e42170"
 # DeepSeek-V4.1-Flash-1017 is a multimodal (vision + text) MoE model. The released checkpoint uses the
 # inference-stack tensor naming (see the repo's inference/model.py), not HF-transformers naming, so