Instructions to use bishmoy/Qwen3-1.7B-ReLU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bishmoy/Qwen3-1.7B-ReLU with Transformers:

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

pipe = pipeline("text-generation", model="bishmoy/Qwen3-1.7B-ReLU")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bishmoy/Qwen3-1.7B-ReLU")
model = AutoModelForCausalLM.from_pretrained("bishmoy/Qwen3-1.7B-ReLU")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bishmoy/Qwen3-1.7B-ReLU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bishmoy/Qwen3-1.7B-ReLU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bishmoy/Qwen3-1.7B-ReLU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bishmoy/Qwen3-1.7B-ReLU

SGLang

How to use bishmoy/Qwen3-1.7B-ReLU 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 "bishmoy/Qwen3-1.7B-ReLU" \
    --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": "bishmoy/Qwen3-1.7B-ReLU",
		"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 "bishmoy/Qwen3-1.7B-ReLU" \
        --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": "bishmoy/Qwen3-1.7B-ReLU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bishmoy/Qwen3-1.7B-ReLU with Docker Model Runner:
```
docker model run hf.co/bishmoy/Qwen3-1.7B-ReLU
```

Qwen3-1.7B-ReLU

This repository contains a ReLU-fied variant of Qwen3 1.7B released as part of the ReLU-Tune project.

The model was created by replacing the transformer MLP activation with ReLU across all decoder layers and then recovering performance through staged LoRA fine-tuning. The weights in this repository are provided as a merged checkpoint for straightforward loading and evaluation.

What This Model Is

Base model: Qwen/Qwen3-1.7B
Architecture change: transformer MLP activations changed to ReLU
Modified layers: all decoder MLP activation sites
Training method: staged LoRA fine-tuning
Training schedule: 2 stages, 900 steps each, 1800 total steps
Training data: continued pretraining on tiiuae/falcon-refinedweb
Model format: merged dense model
Extra metadata: activation_config.json documents the activation modification

Intended Use

This model is intended for:

research on activation functions in large language models
experiments on sparse activations and efficiency tradeoffs
evaluation and fine-tuning workflows built on top of ReLU-Tune

This is primarily a research release, not a production-optimized instruction model.

Files

Typical files in this repository include:

model.safetensors
config.json
generation_config.json
tokenizer.json
tokenizer_config.json
chat_template.jinja
activation_config.json

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "bishmoy/Qwen3-1.7B-ReLU"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

Notes

activation_config.json is included for reproducibility and to document how activations were modified.
This release should follow the base Qwen model's license and usage terms. Users should review and comply with the original model terms before use or redistribution.
Because this is a merged checkpoint, no adapter loading is required for standard inference.

Project

This model was produced with ReLU-Tune, a toolkit for:

full or partial ReLU-fication
staged LoRA fine-tuning
benchmark and perplexity evaluation
activation sparsity measurement

Limitations

This is an experimental model release. ReLU-fication changes the base architecture and can alter behavior in ways that differ from the original dense model. Downstream performance, calibration, and robustness should be validated for any intended use.

Downloads last month: -

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for bishmoy/Qwen3-1.7B-ReLU

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Finetuned

(837)

this model