Instructions to use adamo1139/DeepSeek-R1-0528-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamo1139/DeepSeek-R1-0528-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="adamo1139/DeepSeek-R1-0528-AWQ", 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("adamo1139/DeepSeek-R1-0528-AWQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("adamo1139/DeepSeek-R1-0528-AWQ", trust_remote_code=True)
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 adamo1139/DeepSeek-R1-0528-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adamo1139/DeepSeek-R1-0528-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamo1139/DeepSeek-R1-0528-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adamo1139/DeepSeek-R1-0528-AWQ

SGLang

How to use adamo1139/DeepSeek-R1-0528-AWQ 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 "adamo1139/DeepSeek-R1-0528-AWQ" \
    --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": "adamo1139/DeepSeek-R1-0528-AWQ",
		"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 "adamo1139/DeepSeek-R1-0528-AWQ" \
        --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": "adamo1139/DeepSeek-R1-0528-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adamo1139/DeepSeek-R1-0528-AWQ with Docker Model Runner:
```
docker model run hf.co/adamo1139/DeepSeek-R1-0528-AWQ
```

Glitch Token Issue in DeepSeek-R1-0528-AWQ – Incorrect “极” Character in Long Prompts

by alexchenyu - opened Jul 9, 2025

Discussion

alexchenyu

Jul 9, 2025

Description:
When using adamo1139/DeepSeek-R1-0528-AWQ, I often encounter a glitch during long-prompt inference. Specifically, the output sometimes contains the Chinese character “极” inserted mistakenly in the middle of English text. This appears to be a mis-decoded token (e.g. _St) caused by quantization/tokenizer misalignment.

Steps to Reproduce:

Load one of the AWQ quantized models using vLLM.
Provide a very long English prompt (e.g. >50 K tokens) with code or markdown.
Observe that the response intermittently includes “极” in places where it should not.

Expected Behavior:
The response should contain only English tokens or valid ASCII characters. No Chinese characters like “极” should appear.

Temporary Workaround / Notes:

The glitch seems frequency-related to long input sizes.
I’ve tried clearing caches and ensuring tokenizers from the same commit, but it persists.
Some community discussion suggests tokenizer/embedding offset due to old AWQ tokenizers. A full re-quantization or updating AWQ files might fix it.

Please let me know if there’s a patch/fix, updated model, or recommended workaround. Thanks!

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