Instructions to use Neural-Hacker/Qwen3.5-2B-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Neural-Hacker/Qwen3.5-2B-chat with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-2B")
model = PeftModel.from_pretrained(base_model, "Neural-Hacker/Qwen3.5-2B-chat")

Transformers

How to use Neural-Hacker/Qwen3.5-2B-chat with Transformers:

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

pipe = pipeline("text-generation", model="Neural-Hacker/Qwen3.5-2B-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Neural-Hacker/Qwen3.5-2B-chat", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Neural-Hacker/Qwen3.5-2B-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Neural-Hacker/Qwen3.5-2B-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Neural-Hacker/Qwen3.5-2B-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Neural-Hacker/Qwen3.5-2B-chat

SGLang

How to use Neural-Hacker/Qwen3.5-2B-chat 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 "Neural-Hacker/Qwen3.5-2B-chat" \
    --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": "Neural-Hacker/Qwen3.5-2B-chat",
		"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 "Neural-Hacker/Qwen3.5-2B-chat" \
        --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": "Neural-Hacker/Qwen3.5-2B-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Neural-Hacker/Qwen3.5-2B-chat with Docker Model Runner:
```
docker model run hf.co/Neural-Hacker/Qwen3.5-2B-chat
```

Qwen3.5-2B Chat LoRA (Ultrachat SFT)

Overview

LoRA fine-tuned model based on Qwen/Qwen3.5-2B
Trained for chat-style instruction following
Uses conversational formatting (<|user|>, <|assistant|>)
Optimized for fast training with a reduced dataset subset

Important

This repository contains LoRA adapter weights only
Base model is NOT included
Required base model: Qwen/Qwen3.5-2B

Usage

Load base model and adapter
Use chat template for proper responses

from transformers import AutoTokenizer, AutoModelForCausalLM  
from peft import PeftModel  

base_model = "Qwen/Qwen3.5-2B"  
adapter = "your-username/your-repo-name"  

tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)  

model = AutoModelForCausalLM.from_pretrained(  
    base_model,  
    torch_dtype=torch.float16,  
    device_map="auto",  
    trust_remote_code=True  
)  

model = PeftModel.from_pretrained(model, adapter)  
model.eval()  

messages = [  
    {"role": "user", "content": "Explain gravity briefly"}  
]  

text = tokenizer.apply_chat_template(  
    messages,  
    tokenize=False,  
    add_generation_prompt=True  
)  

inputs = tokenizer(text, return_tensors="pt").to(model.device)  

outputs = model.generate(  
    **inputs,  
    max_new_tokens=400,  
    do_sample=True,  
    temperature=0.7,  
    top_p=0.9,  
    eos_token_id=tokenizer.eos_token_id  
)  

response = tokenizer.decode(outputs[0], skip_special_tokens=True)  

if "</think>" in response:  
    response = response.split("</think>")[-1]  

response = response.replace(text, "").strip()  

print(response)

Training Details

Base Model: Qwen/Qwen3.5-2B
Method: LoRA (PEFT)
Framework: Transformers + TRL (SFTTrainer)
Dataset: HuggingFaceH4/ultrachat_200k (train_sft split)
Data Used: 10,000 samples (subset for fast training)
Task: Chat-style supervised fine-tuning

Hyperparameters

Max Steps: 1000
Max Sequence Length: 1024
Batch Size: 4
Gradient Accumulation: 4
Learning Rate: 2e-4
Precision: bfloat16
Gradient Checkpointing: Enabled

Capabilities

Multi-turn conversational responses
Instruction-following chat behavior
Handles both short and long-form answers
Supports English and Hindi inputs (inherited from base model)

Limitations

Trained on a subset (10k samples), not full dataset
May produce inconsistent or incomplete responses
Not fully aligned for safety or factual accuracy
May still show verbosity or repetition

Example

Input: What is gravity?
Output: Gravity is a fundamental force that attracts objects with mass toward each other.

Model Type

Architecture: Causal Language Model
Task: Text Generation (Chat-style)
Fine-tuning: LoRA Adapter

License

This model is released under the CC BY-NC 4.0 license.

Downloads last month: 23

Model tree for Neural-Hacker/Qwen3.5-2B-chat

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Adapter

(77)

this model

Neural-Hacker
/

Qwen3.5-2B-chat