Instructions to use ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g with Transformers:

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

pipe = pipeline("text-generation", model="ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g", 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("ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g", 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 ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g

SGLang

How to use ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g 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 "ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g" \
    --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": "ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g",
		"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 "ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g" \
        --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": "ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g with Docker Model Runner:
```
docker model run hf.co/ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g
```

SpiridonSunRotator commited on Apr 7, 2025

Commit

ac66d87

verified ·

1 Parent(s): 56364b2

Added eval reproduction and description

Browse files

Files changed (1) hide show

README.md +51 -1

README.md CHANGED Viewed

@@ -1,7 +1,27 @@
 ### Evaluation
-This model was evaluated on the OpenLLM v1 benchmarks and reasoning tasks (AIME24, GPQA-Diamond, MATH500) . Model outputs were generated with the vLLM engine.
 `OpenLLM v1`
 |      Model                         | ArcC | GSM8k | Hellaswag | MMLU | TruthfulQA-mc2 | Winogrande | Average | Recovery |
@@ -16,3 +36,33 @@ This model was evaluated on the OpenLLM v1 benchmarks and reasoning tasks (AIME2
 | deepseek-ai/DeepSeek-R1                       |     78.34       |       97.24     |        73.383       |  82.99  |   100.00    |
 | cognitivecomputations/DeepSeek-R1-AWQ |     70.67      |       93.64     |        70.456       |  78.25  |  94.29   |
 | daslab-testing/DeepSeek-R1-GPTQ-4b-128g (this)            |  72.96    |    97.08  |        70.26        |  80.10   |  96.52   |

+---
+license: mit
+library_name: transformers
+---
+# DeepSeek-R1-GPTQ-4b-128g
+<!-- markdownlint-disable first-line-h1 -->
+<!-- markdownlint-disable html -->
+<!-- markdownlint-disable no-duplicate-header -->
+## Model Overview
+This model was obtained by quantizing the weights of [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.
+All layers within transformer blocks are compressed. Weights are quantized using a symmetric per-group scheme, with group size 128. The GPTQ algorithm is applied for quantization.
+Model checkpoint is saved in [compressed_tensors](https://github.com/neuralmagic/compressed-tensors) format.
 ### Evaluation
+This model was evaluated on the OpenLLM v1 benchmarks and reasoning tasks (AIME-24, GPQA-Diamond, MATH-500).
+Model outputs were generated with the vLLM engine.
+For reasoning tasks we sample 10 solutions for each seed with `temperature=0.6`, `top_p=0.95` and `max_new_tokens=32768`.
 `OpenLLM v1`
 |      Model                         | ArcC | GSM8k | Hellaswag | MMLU | TruthfulQA-mc2 | Winogrande | Average | Recovery |
 | deepseek-ai/DeepSeek-R1                       |     78.34       |       97.24     |        73.383       |  82.99  |   100.00    |
 | cognitivecomputations/DeepSeek-R1-AWQ |     70.67      |       93.64     |        70.456       |  78.25  |  94.29   |
 | daslab-testing/DeepSeek-R1-GPTQ-4b-128g (this)            |  72.96    |    97.08  |        70.26        |  80.10   |  96.52   |
+## Reproduction
+The results were obtained using the following commands:
+`OpenLLM v1`
+```bash
+MODEL=ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g
+MODEL_ARGS="pretrained=$MODEL,max_model_len=4096,tensor_parallel_size=8,dtype=auto,gpu_memory_utilization=0.80"
+lm_eval \
+  --model vllm \
+  --model_args $MODEL_ARGS \
+  --tasks openllm \
+  --batch_size auto
+```
+For reasoning evals we adopted the protocol from the [open-r1 repository](https://github.com/huggingface/open-r1).
+`Reasoning tasks`
+```bash
+MODEL=ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g
+MODEL_ARGS="pretrained=$MODEL,max_model_length=38768,gpu_memory_utilization=0.8,tensor_parallel_size=1,add_special_tokens=false,generation_parameters={\"max_new_tokens\":32768,\"temperature\":0.6,\"top_p\":0.95,\"seed\":7686}"
+TASK=(one of aime24,math_500,gpqa:diamond)
+lighteval vllm $MODEL_ARGS "custom|$TASK|0|0" \
+    --custom-tasks src/open_r1/evaluate.py \
+    --use-chat-template \
+    --output-dir $OUTPUT_DIR
+```