Instructions to use qubitron/LLaDA-8B-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qubitron/LLaDA-8B-Quantized with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="qubitron/LLaDA-8B-Quantized")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("qubitron/LLaDA-8B-Quantized", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use qubitron/LLaDA-8B-Quantized with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "qubitron/LLaDA-8B-Quantized" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "qubitron/LLaDA-8B-Quantized", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/qubitron/LLaDA-8B-Quantized
- SGLang
How to use qubitron/LLaDA-8B-Quantized 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 "qubitron/LLaDA-8B-Quantized" \ --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": "qubitron/LLaDA-8B-Quantized", "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 "qubitron/LLaDA-8B-Quantized" \ --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": "qubitron/LLaDA-8B-Quantized", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use qubitron/LLaDA-8B-Quantized with Docker Model Runner:
docker model run hf.co/qubitron/LLaDA-8B-Quantized
Add INT8 and INT4 quantized weights
Browse files- llada_int4_quantized.pt +3 -0
- llada_int8_quantized.pt +3 -0
llada_int4_quantized.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b42f17257baa051badbedd1d4e577fe868a8fa9fc834efb3c7a54ffca9538685
|
| 3 |
+
size 4788526525
|
llada_int8_quantized.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5c9b729256e750902a8a91033deecacd091d2b8779a325828580aa9476eb3be
|
| 3 |
+
size 8537189053
|