Instructions to use ertghiu256/Qwen3.5-2b-ReMix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ertghiu256/Qwen3.5-2b-ReMix with Transformers:

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

pipe = pipeline("image-text-to-text", model="ertghiu256/Qwen3.5-2b-ReMix")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("ertghiu256/Qwen3.5-2b-ReMix")
model = AutoModelForImageTextToText.from_pretrained("ertghiu256/Qwen3.5-2b-ReMix")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ertghiu256/Qwen3.5-2b-ReMix with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ertghiu256/Qwen3.5-2b-ReMix"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ertghiu256/Qwen3.5-2b-ReMix",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ertghiu256/Qwen3.5-2b-ReMix

SGLang

How to use ertghiu256/Qwen3.5-2b-ReMix 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 "ertghiu256/Qwen3.5-2b-ReMix" \
    --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": "ertghiu256/Qwen3.5-2b-ReMix",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "ertghiu256/Qwen3.5-2b-ReMix" \
        --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": "ertghiu256/Qwen3.5-2b-ReMix",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio new

How to use ertghiu256/Qwen3.5-2b-ReMix with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ertghiu256/Qwen3.5-2b-ReMix to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ertghiu256/Qwen3.5-2b-ReMix to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ertghiu256/Qwen3.5-2b-ReMix to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="ertghiu256/Qwen3.5-2b-ReMix",
    max_seq_length=2048,
)

Docker Model Runner
How to use ertghiu256/Qwen3.5-2b-ReMix with Docker Model Runner:
```
docker model run hf.co/ertghiu256/Qwen3.5-2b-ReMix
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🚀 Qwen3.5-2B-ReMix (Reasoning Mix) 🧠

This repository contains a fully merged, native Float16 (F16) fine-tune of Qwen/Qwen3.5-2B 🤖. The primary objective of this model is to significantly scale up performance on complex reasoning tasks, specifically targeting advanced mathematics 🧮, logical deduction, and structured coding problems 💻.

By leveraging multi-source open-source distillation data, it aims to achieve "frontier-style" reasoning capabilities while keeping the footprint compact enough to run smoothly at native speeds on local, everyday consumer hardware 🏠 without the need for external adapters.

🌟 Model Highlights

🏗️ Base Architecture: Qwen/Qwen3.5-2B (Dense, Hybrid Gated DeltaNet)
💾 Precision format: Native Float16 (F16) Merged Weights — No adapter required!
🎯 Main Goal: Advanced mathematical reasoning and complex code generation/debugging.
🛡️ Data Origin: 100% open-source distilled reasoning datasets natively hosted on Hugging Face. No proprietary data or closed APIs (OpenAI, Anthropic, Google) were used or involved in the collection or training process.
⚡ Target Environment: Local, high-efficiency edge execution with minimal hardware requirements.

🎛️ Recommended Generation Parameters

Depending on your use case, we recommend switching between "Everyday" and "Deep Reasoning" profiles to get the best performance out of the 2B architecture.

🏠 Everyday Use (Balanced)

Parameter	Value	Note
🌡️ Temperature (`temp`)	`0.4`	Provides a balance of creativity and coherence.
🎯 Top K (`top_k`)	`30`	Limits vocabulary to the most probable next steps.
🔄 Repeat Penalty	`1.1`	Light penalty to ensure conversational flow.

🧠 Deep Reasoning

Parameter	Value	Note
🌡️ Temperature (`temp`)	`0.0 - 0.1`	Forced determinism for strict logical consistency.
🎯 Top K (`top_k`)	`60`	Wider pool for complex technical vocabulary.
🔄 Repeat Penalty	`1.2`	Prevents "reasoning loops" during long chain-of-thought.

📊 Training & Merge Details

The model was adapted using Parameter-Efficient Fine-Tuning (PEFT) and then compiled back into the core network layers to output clean, unified F16 weights via Unsloth.

🔄 Training Steps: 175
📉 Loss Profile: Convergence floor reached ~0.58; stabilized consistently around 0.85
📈 Learning Rate: 4e-5
📐 LoRA Rank ($R$) during training: 16
⚖️ LoRA Alpha ($\alpha$) during training: 32

⚠️ Limitations & Risks

While this fine-tune aggressively pushes the boundaries of what a 2B parameter model can achieve locally, users should carefully account for the following behaviors:

🔮 Hallucinations: Like all highly compact models, it can confidently present false calculations or flawed code as absolute facts. Always verify outputs.
🎭 Inconsistent Styles: Due to the "ReMix" nature of the training data, the model may occasionally exhibit shifting output structures or stylistic variations.
🛑 Logic Mismatches: For extremely niche programming or high-level academic proofs, the model may occasionally produce broken syntax or reverse its logical assertions.

📦 How to Use Natively

🐍 Using Hugging Face Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_path = "YOUR_USERNAME/Qwen3.5-2B-ReMix"

# Load the aligned tokenizer and model weights directly
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path, 
    torch_dtype=torch.float16, 
    device_map="auto"
)

messages = [
    {"role": "user", "content": "Explain the logic of a quicksort algorithm and implement it in Python."}
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Using Reasoning Parameters (To not overthink)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=1024,
    temperature=0.1,    
    top_k=60,           
    repeat_penalty=1.2  
)

Uploaded finetuned model

Developed by: ertghiu256
License: apache-2.0
Finetuned from model : unsloth/Qwen3.5-2B

This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 130

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for ertghiu256/Qwen3.5-2b-ReMix

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

(180)

this model

Finetunes

1 model

Quantizations

2 models

ertghiu256
/

Qwen3.5-2b-ReMix