Instructions to use deepseek-ai/deepseek-coder-33b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/deepseek-coder-33b-base with Transformers:

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

pipe = pipeline("text-generation", model="deepseek-ai/deepseek-coder-33b-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-base")
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/deepseek-coder-33b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/deepseek-coder-33b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/deepseek-coder-33b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/deepseek-coder-33b-base

SGLang

How to use deepseek-ai/deepseek-coder-33b-base 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-coder-33b-base" \
    --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": "deepseek-ai/deepseek-coder-33b-base",
		"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 "deepseek-ai/deepseek-coder-33b-base" \
        --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": "deepseek-ai/deepseek-coder-33b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepseek-ai/deepseek-coder-33b-base with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/deepseek-coder-33b-base
```

Tokenizer issues

by sanderland - opened May 8, 2024

Discussion

sanderland

May 8, 2024

•

edited May 8, 2024

from transformers import AutoTokenizer
tid = 31750
for use_fast in [False,True]:
    tok = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-base", use_fast=use_fast)
    decoded = tok.decode([tid])
    reencoded = [(i,tok.decode([i])) for i in tok.encode(s, add_special_tokens=False)]
    print(f"{use_fast=}\t{tid=} {decoded=} {reencoded=}")

Gives

use_fast=False	tid=31750 decoded=' indústria' reencoded=[(1539, ' ind'), (32007, '�'), (292, 'st'), (2122, 'ria')]
use_fast=True	tid=31750 decoded=' indústria' reencoded=[(1539, ' ind'), (32007, '�'), (292, 'st'), (2122, 'ria')]

It seems the tokens at the end were an attempt to manually add missing (but unused) UTF-8 bytes, but they were instead mapped to the unicode points, and are overriding other tokens.
The non-code models are similarly affected.

sanderland

May 27, 2024

Apparently fixed in the llm/math models, but a wont-fix in code. cf https://github.com/huggingface/tokenizers/issues/1392

sanderland changed discussion status to closed May 27, 2024

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