Instructions to use debaterhub/prefix-einstein-40 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use debaterhub/prefix-einstein-40 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-30B-A3B-Thinking-2507")
model = PeftModel.from_pretrained(base_model, "debaterhub/prefix-einstein-40")

Transformers

How to use debaterhub/prefix-einstein-40 with Transformers:

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

pipe = pipeline("text-generation", model="debaterhub/prefix-einstein-40")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("debaterhub/prefix-einstein-40", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use debaterhub/prefix-einstein-40 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "debaterhub/prefix-einstein-40"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "debaterhub/prefix-einstein-40",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/debaterhub/prefix-einstein-40

SGLang

How to use debaterhub/prefix-einstein-40 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 "debaterhub/prefix-einstein-40" \
    --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": "debaterhub/prefix-einstein-40",
		"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 "debaterhub/prefix-einstein-40" \
        --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": "debaterhub/prefix-einstein-40",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use debaterhub/prefix-einstein-40 with Docker Model Runner:
```
docker model run hf.co/debaterhub/prefix-einstein-40
```

prefix-einstein-40 / adapter_config.json

dgonier

Upload folder using huggingface_hub

7f4da52 verified 5 months ago

raw

history blame contribute delete

443 Bytes

	{
	"auto_mapping": null,
	"base_model_name_or_path": "Qwen/Qwen3-30B-A3B-Thinking-2507",
	"encoder_hidden_size": 2048,
	"inference_mode": true,
	"modules_to_save": null,
	"num_attention_heads": 4,
	"num_layers": 48,
	"num_transformer_submodules": 1,
	"num_virtual_tokens": 40,
	"peft_type": "PREFIX_TUNING",
	"peft_version": "0.18.0",
	"prefix_projection": true,
	"revision": null,
	"task_type": "CAUSAL_LM",
	"token_dim": 512
	}