Instructions to use deepseek-ai/deepseek-llm-67b-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-llm-67b-chat with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/deepseek-llm-67b-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-llm-67b-chat")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-llm-67b-chat")
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 deepseek-ai/deepseek-llm-67b-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/deepseek-llm-67b-chat"
# 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/deepseek-llm-67b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-llm-67b-chat

SGLang

How to use deepseek-ai/deepseek-llm-67b-chat 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/deepseek-llm-67b-chat" \
    --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/deepseek-llm-67b-chat",
		"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/deepseek-llm-67b-chat" \
        --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/deepseek-llm-67b-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-llm-67b-chat with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-llm-67b-chat
```

tokenizer.model

by RonanMcGovern - opened Dec 5, 2023

Discussion

RonanMcGovern

Dec 5, 2023

Could you upload a tokenizer.model file so we can make ggufs of fine-tunes? Thanks

luofuli

Feb 4, 2024

Why don‘t we provide the tokenizer.model file for model quantization?

DeepSeek LLM utilizes the HuggingFace Tokenizer to implement the Byte-level BPE algorithm, with specially designed pre-tokenizers to ensure optimal performance. Currently, there is no direct way to convert the tokenizer into a SentencePiece tokenizer. We are contributing to the open-source quantization methods facilitate the usage of HuggingFace Tokenizer.

GGUF(llama.cpp)

We have submitted a PR to the popular quantization repository llama.cpp to fully support all HuggingFace pre-tokenizers, including ours.

While waiting for the PR to be merged, you can generate your GGUF model using the following steps:

git clone https://github.com/DOGEwbx/llama.cpp.git
cd llama.cpp
git checkout regex_gpt2_preprocess
# set up the environment according to README
make
python3 -m pip install -r requirements.txt
# generate GGUF model
python convert-hf-to-gguf.py <MODEL_PATH> --outfile <GGUF_PATH> --model-name deepseekllm
# use q4_0 quantization as an example
./quantize <GGUF_PATH> <OUTPUT_PATH> q4_0
./main -m <OUTPUT_PATH> -n 128 -p <PROMPT>

GPTQ(exllamav2)

UPDATE:exllamav2 has been able to support HuggingFace Tokenizer. Please pull the latest version and try out.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment