Instructions to use Jerry-lin23/deepseek-leetcode-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jerry-lin23/deepseek-leetcode-3 with Transformers:

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

pipe = pipeline("text-generation", model="Jerry-lin23/deepseek-leetcode-3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jerry-lin23/deepseek-leetcode-3")
model = AutoModelForCausalLM.from_pretrained("Jerry-lin23/deepseek-leetcode-3")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jerry-lin23/deepseek-leetcode-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jerry-lin23/deepseek-leetcode-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jerry-lin23/deepseek-leetcode-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jerry-lin23/deepseek-leetcode-3

SGLang

How to use Jerry-lin23/deepseek-leetcode-3 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 "Jerry-lin23/deepseek-leetcode-3" \
    --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": "Jerry-lin23/deepseek-leetcode-3",
		"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 "Jerry-lin23/deepseek-leetcode-3" \
        --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": "Jerry-lin23/deepseek-leetcode-3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jerry-lin23/deepseek-leetcode-3 with Docker Model Runner:
```
docker model run hf.co/Jerry-lin23/deepseek-leetcode-3
```

Jerry-lin23 commited on Dec 22, 2025

Commit

53d6d45

verified ·

1 Parent(s): 8e77ef2

Upload LlamaForCausalLM

Browse files

Files changed (2) hide show

config.json +15 -0
model.safetensors +3 -0

config.json CHANGED Viewed

@@ -19,6 +19,21 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "factor": 4.0,

   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": {
     "factor": 4.0,

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:20e8ebd9c3e3165540e3f5f29822f6d71d6a992d9c1d9a00da1aca954dc7dd51
+size 4171916320