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

Libraries

How to use yujiepan/deepseek-v4-tiny-random with Transformers:

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

pipe = pipeline("text-generation", model="yujiepan/deepseek-v4-tiny-random")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yujiepan/deepseek-v4-tiny-random")
model = AutoModelForCausalLM.from_pretrained("yujiepan/deepseek-v4-tiny-random")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yujiepan/deepseek-v4-tiny-random with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yujiepan/deepseek-v4-tiny-random

SGLang

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

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

deepseek-v4-tiny-random

File size: 947 Bytes

e44adc3

{
  "max_batch_size": 4,
  "max_seq_len": 65536,
  "dtype": "fp8",
  "scale_fmt": "ue8m0",
  "expert_dtype": "fp4",
  "scale_dtype": "fp8",
  "vocab_size": 129280,
  "dim": 128,
  "moe_inter_dim": 256,
  "n_layers": 7,
  "n_hash_layers": 3,
  "n_mtp_layers": 1,
  "n_heads": 8,
  "n_routed_experts": 32,
  "n_shared_experts": 1,
  "n_activated_experts": 6,
  "score_func": "sqrtsoftplus",
  "route_scale": 1.5,
  "swiglu_limit": 10.0,
  "q_lora_rank": 128,
  "head_dim": 128,
  "rope_head_dim": 64,
  "norm_eps": 1e-06,
  "o_groups": 8,
  "o_lora_rank": 128,
  "window_size": 128,
  "compress_ratios": [
    0,
    0,
    4,
    128,
    4,
    128,
    4,
    0
  ],
  "compress_rope_theta": 160000.0,
  "original_seq_len": 65536,
  "rope_theta": 10000.0,
  "rope_factor": 16.0,
  "beta_fast": 32,
  "beta_slow": 1,
  "index_n_heads": 4,
  "index_head_dim": 128,
  "index_topk": 512,
  "hc_mult": 4,
  "hc_sinkhorn_iters": 20,
  "hc_eps": 1e-06
}