Instructions to use fenglui/DeepCoder-1.5B-Preview-16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fenglui/DeepCoder-1.5B-Preview-16bit with Transformers:

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

pipe = pipeline("text-generation", model="fenglui/DeepCoder-1.5B-Preview-16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fenglui/DeepCoder-1.5B-Preview-16bit")
model = AutoModelForCausalLM.from_pretrained("fenglui/DeepCoder-1.5B-Preview-16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fenglui/DeepCoder-1.5B-Preview-16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fenglui/DeepCoder-1.5B-Preview-16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fenglui/DeepCoder-1.5B-Preview-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fenglui/DeepCoder-1.5B-Preview-16bit

SGLang

How to use fenglui/DeepCoder-1.5B-Preview-16bit 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 "fenglui/DeepCoder-1.5B-Preview-16bit" \
    --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": "fenglui/DeepCoder-1.5B-Preview-16bit",
		"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 "fenglui/DeepCoder-1.5B-Preview-16bit" \
        --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": "fenglui/DeepCoder-1.5B-Preview-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fenglui/DeepCoder-1.5B-Preview-16bit with Docker Model Runner:
```
docker model run hf.co/fenglui/DeepCoder-1.5B-Preview-16bit
```

fenglui commited on Apr 15, 2025

Commit

3c462cb

verified ·

1 Parent(s): 8bbf1c8

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -6

README.md CHANGED Viewed

@@ -2,20 +2,22 @@
 license: mit
 library_name: transformers
 datasets:
-  - PrimeIntellect/verifiable-coding-problems
-  - likaixin/TACO-verified
-  - livecodebench/code_generation_lite
 language:
-  - en
 base_model:
-  - agentica-org/DeepCoder-1.5B-Preview
 base_model_relation: quantized
 pipeline_tag: text-generation
 ---
 <div align="center">
-<span style="font-family: default; font-size: 1.5em;">DeepCoder-1.5B-Preview</span>
 <div>
 🚀 Democratizing Reinforcement Learning for LLMs (RLLM) 🌟
 </div>

 license: mit
 library_name: transformers
 datasets:
+- PrimeIntellect/verifiable-coding-problems
+- likaixin/TACO-verified
+- livecodebench/code_generation_lite
 language:
+- en
 base_model:
+- agentica-org/DeepCoder-1.5B-Preview
 base_model_relation: quantized
 pipeline_tag: text-generation
+tags:
+- 16bit
 ---
 <div align="center">
+<span style="font-family: default; font-size: 1.5em;">DeepCoder-1.5B-Preview  (16bit)</span>
 <div>
 🚀 Democratizing Reinforcement Learning for LLMs (RLLM) 🌟
 </div>