Text Generation
Transformers
Safetensors
deepseek_v3
DeepSeek-R1-0528
GPTQ
Int4-Int8Mix
量化修复
vLLM
conversational
custom_code
text-generation-inference
4-bit precision
gptq
Instructions to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact
- SGLang
How to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact 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 "QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact" \ --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": "QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", "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 "QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact" \ --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": "QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact with Docker Model Runner:
docker model run hf.co/QuantTrio/DeepSeek-R1-0528-GPTQ-Int4-Int8Mix-Compact
Commit History
-
Upload model-00067-of-00090.safetensors with huggingface_hub
Verified signature4efbcff -
Upload model-00068-of-00090.safetensors with huggingface_hub
Verified signatured4590a2 -
Upload model-00064-of-00090.safetensors with huggingface_hub
Verified signature2aa5b07 -
Upload model-00066-of-00090.safetensors with huggingface_hub
Verified signature0076a4d -
Upload model-00065-of-00090.safetensors with huggingface_hub
Verified signaturec2a5098 -
Upload model-00063-of-00090.safetensors with huggingface_hub
Verified signature4e79993 -
Upload model-00059-of-00090.safetensors with huggingface_hub
Verified signature908023a -
Upload model-00062-of-00090.safetensors with huggingface_hub
Verified signature5a8a4ca -
Upload model-00061-of-00090.safetensors with huggingface_hub
Verified signatured645c2b -
Upload model-00060-of-00090.safetensors with huggingface_hub
Verified signatureb4367ce -
Upload model-00058-of-00090.safetensors with huggingface_hub
Verified signature24b81f5 -
Upload model-00057-of-00090.safetensors with huggingface_hub
Verified signature5ef1725 -
Upload model-00056-of-00090.safetensors with huggingface_hub
Verified signature2e3258a -
Upload model-00055-of-00090.safetensors with huggingface_hub
Verified signature5fb42c9 -
Upload model-00054-of-00090.safetensors with huggingface_hub
Verified signature73b2773 -
Upload model-00052-of-00090.safetensors with huggingface_hub
Verified signature9cf7ae0 -
Upload model-00053-of-00090.safetensors with huggingface_hub
Verified signature3b95625 -
Upload model-00050-of-00090.safetensors with huggingface_hub
Verified signature46a57d6 -
Upload model-00051-of-00090.safetensors with huggingface_hub
Verified signaturee653972 -
Upload model-00048-of-00090.safetensors with huggingface_hub
Verified signature4651d44 -
Upload model-00047-of-00090.safetensors with huggingface_hub
Verified signature2e882d2 -
Upload model-00049-of-00090.safetensors with huggingface_hub
Verified signature7b43a5e -
Upload model-00046-of-00090.safetensors with huggingface_hub
Verified signature02225e8 -
Upload model-00045-of-00090.safetensors with huggingface_hub
Verified signature78a2d4b -
Upload model-00044-of-00090.safetensors with huggingface_hub
Verified signature883de8b -
Upload model-00040-of-00090.safetensors with huggingface_hub
Verified signatureec65f7f -
Upload model-00043-of-00090.safetensors with huggingface_hub
Verified signaturec9cd8e2 -
Upload model-00042-of-00090.safetensors with huggingface_hub
Verified signature63be396 -
Upload model-00041-of-00090.safetensors with huggingface_hub
Verified signature4213245 -
Upload model-00039-of-00090.safetensors with huggingface_hub
Verified signature1d76694 -
Upload model-00038-of-00090.safetensors with huggingface_hub
Verified signaturea3b4bd2 -
Upload model-00036-of-00090.safetensors with huggingface_hub
Verified signature5bce660 -
Upload model-00037-of-00090.safetensors with huggingface_hub
Verified signaturee93f698 -
Upload model-00035-of-00090.safetensors with huggingface_hub
Verified signature5b4a1ea -
Upload model-00033-of-00090.safetensors with huggingface_hub
Verified signature6168895 -
Upload model-00034-of-00090.safetensors with huggingface_hub
Verified signaturebb527ed -
Upload model-00032-of-00090.safetensors with huggingface_hub
Verified signature2b9fd05 -
Upload model-00031-of-00090.safetensors with huggingface_hub
Verified signature089fde9 -
Upload model-00029-of-00090.safetensors with huggingface_hub
Verified signaturef2fb74a -
Upload model-00030-of-00090.safetensors with huggingface_hub
Verified signature70fe781 -
Upload model-00028-of-00090.safetensors with huggingface_hub
Verified signature78da94d -
Upload model-00026-of-00090.safetensors with huggingface_hub
Verified signatured7fbfe5 -
Upload model-00027-of-00090.safetensors with huggingface_hub
Verified signature4c5ebe9 -
Upload model-00025-of-00090.safetensors with huggingface_hub
Verified signature93e861a -
Upload model-00021-of-00090.safetensors with huggingface_hub
Verified signatureed7bfb5 -
Upload model-00024-of-00090.safetensors with huggingface_hub
Verified signature988a4b9 -
Upload model-00023-of-00090.safetensors with huggingface_hub
Verified signature5ed402d -
Upload model-00022-of-00090.safetensors with huggingface_hub
Verified signature3d61ab8 -
Upload model-00020-of-00090.safetensors with huggingface_hub
Verified signature5f420f9 -
Upload model-00017-of-00090.safetensors with huggingface_hub
Verified signaturef3f4c7d