Instructions to use deepseek-ai/ESFT-token-code-lite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/ESFT-token-code-lite with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/ESFT-token-code-lite", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/ESFT-token-code-lite", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/ESFT-token-code-lite", trust_remote_code=True, device_map="auto")
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 Settings

vLLM

How to use deepseek-ai/ESFT-token-code-lite with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/ESFT-token-code-lite"
# 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/ESFT-token-code-lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/ESFT-token-code-lite

SGLang

How to use deepseek-ai/ESFT-token-code-lite 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/ESFT-token-code-lite" \
    --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/ESFT-token-code-lite",
		"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/ESFT-token-code-lite" \
        --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/ESFT-token-code-lite",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/ESFT-token-code-lite with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/ESFT-token-code-lite
```

ESFT-token-code-lite / expert_cfg.json

ZihanWang314

Upload folder using huggingface_hub

71cd39e verified about 2 years ago

Raw

History Blame Contribute Delete

1.14 kB

{"experts": {"1": [24, 32, 6, 33, 30, 62, 28, 44, 55], "2": [57, 47, 34, 39, 30, 45, 35, 48, 13, 37, 41], "3": [29, 20, 1, 36, 23, 54, 9, 49, 22, 31], "4": [48, 35, 60, 40, 24, 63, 22, 55, 59], "5": [14, 10, 25, 34, 56, 53, 38, 12, 59, 21], "6": [4, 25, 59, 34, 20, 11, 55, 50, 6], "7": [13, 5, 28, 47, 26, 61, 21, 4, 55], "8": [1, 27, 11, 8, 55, 18, 2, 53], "9": [26, 11, 53, 1, 56, 61, 59, 48], "10": [63, 44, 50, 45, 10, 30, 17, 58], "11": [30, 63, 58, 5, 52, 39, 53], "12": [58, 46, 52, 7, 15, 18, 30, 42], "13": [19, 37, 55, 23, 40, 38, 61], "14": [43, 11, 53, 30, 56, 37, 33], "15": [59, 9, 18, 16, 19, 15, 32], "16": [10, 55, 20, 14, 22, 54, 25, 48], "17": [6, 51, 17, 36, 25, 2, 35, 58, 52], "18": [0, 9, 27, 6, 21, 34, 16], "19": [32, 7, 57, 20, 52, 4, 14, 47, 12], "20": [27, 50, 16, 32, 7, 19, 21, 23], "21": [44, 41, 48, 35, 25, 59, 55, 27], "22": [23, 62, 36, 40, 53, 0, 9, 16, 12, 5], "23": [25, 50, 42, 54, 51, 18, 33, 35], "24": [16, 34, 39, 55, 51, 9, 12, 54, 23, 13], "25": [51, 58, 27, 44, 35, 17, 16, 31, 40, 1], "26": [23, 19, 16, 50, 47, 12, 60, 42, 58, 18]}, "shared_experts": false, "non_expert_modules": false}