Instructions to use mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant with Transformers:

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

pipe = pipeline("text-generation", model="mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant

SGLang

How to use mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant 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 "mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant" \
    --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": "mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant",
		"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 "mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant" \
        --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": "mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant with Docker Model Runner:
```
docker model run hf.co/mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant
```

PTD Qwen2.5-0.5B Keep70 Variant

PTD (Physical Token Dropping) keep-rate 70% variant of Qwen2.5-0.5B.

Base model: Qwen/Qwen2.5-0.5B
Variant: PTD keep70 (full-state)
Recommended keep-rate: 0.7
Runtime: custom HF remote code (trust_remote_code=True)

Repository Links

GitHub project: https://github.com/mhndayesh/Physical-Token-Dropping-PTD
PTD engineering docs: https://github.com/mhndayesh/Physical-Token-Dropping-PTD/tree/main/FINAL_ENG_DOCS

What Is Included

ptd_model_state.pt: full PTD model weights (base + PTD components)
config.json: HF auto-map for custom loading
configuration_ptd_qwen2.py, modeling_ptd_qwen2.py: HF custom classes
model.py: PTD runtime implementation
ptd_package_config.json: package metadata and PTD config

Quick Start (Transformers)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant"

model = AutoModelForCausalLM.from_pretrained(
    repo,
    trust_remote_code=True,
    dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
)

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B")
inputs = tokenizer("PTD cache test:", return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=32, do_sample=False, use_cache=True)
print(tokenizer.decode(out[0], skip_special_tokens=True))

Notes

This model uses PTD sparse routing and custom runtime behavior.
For reproducibility commands and benchmarks, see the GitHub docs linked above.

Downloads last month: 3

Model tree for mhndayesh/PTD-Qwen2.5-0.5B-Keep70-Variant

Base model

Qwen/Qwen2.5-0.5B

Finetuned

(617)

this model