Instructions to use Proximile/LLaDA-8B-Tools with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Proximile/LLaDA-8B-Tools with Transformers:

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

pipe = pipeline("text-generation", model="Proximile/LLaDA-8B-Tools", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Proximile/LLaDA-8B-Tools", trust_remote_code=True, dtype="auto")

PEFT
How to use Proximile/LLaDA-8B-Tools with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Proximile/LLaDA-8B-Tools with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Proximile/LLaDA-8B-Tools"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Proximile/LLaDA-8B-Tools",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Proximile/LLaDA-8B-Tools

SGLang

How to use Proximile/LLaDA-8B-Tools 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 "Proximile/LLaDA-8B-Tools" \
    --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": "Proximile/LLaDA-8B-Tools",
		"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 "Proximile/LLaDA-8B-Tools" \
        --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": "Proximile/LLaDA-8B-Tools",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Proximile/LLaDA-8B-Tools with Docker Model Runner:
```
docker model run hf.co/Proximile/LLaDA-8B-Tools
```

ProximileAdmin commited on May 15, 2025

Commit

07555c7

verified ·

1 Parent(s): a89f370

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -21,6 +21,8 @@ tags:
 This repository contains a variant of the [GSAI-ML/LLaDA-8B-Instruct](https://huggingface.co/GSAI-ML/LLaDA-8B-Instruct) model, fine-tuned by [Proximile LLC](https://proximile.llc) to enhance its tool calling capabilities. Proximile specializes in secure, on-premise AI solutions for small and medium-sized businesses.
 ## About LLaDA
 LLaDA (Language Large Discrete Diffusion Applied) is a novel language model architecture that uses discrete diffusion for text generation. Unlike traditional autoregressive models, LLaDA generates text through an iterative denoising process, progressively replacing mask tokens with predicted tokens based on confidence scores.

 This repository contains a variant of the [GSAI-ML/LLaDA-8B-Instruct](https://huggingface.co/GSAI-ML/LLaDA-8B-Instruct) model, fine-tuned by [Proximile LLC](https://proximile.llc) to enhance its tool calling capabilities. Proximile specializes in secure, on-premise AI solutions for small and medium-sized businesses.
+![Demo](demo.gif)
 ## About LLaDA
 LLaDA (Language Large Discrete Diffusion Applied) is a novel language model architecture that uses discrete diffusion for text generation. Unlike traditional autoregressive models, LLaDA generates text through an iterative denoising process, progressively replacing mask tokens with predicted tokens based on confidence scores.