Instructions to use emretmrk/Qwen3.5-4B-TR-Finance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emretmrk/Qwen3.5-4B-TR-Finance with Transformers:

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

pipe = pipeline("image-text-to-text", model="emretmrk/Qwen3.5-4B-TR-Finance")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("emretmrk/Qwen3.5-4B-TR-Finance")
model = AutoModelForCausalLM.from_pretrained("emretmrk/Qwen3.5-4B-TR-Finance", device_map="auto")
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 = 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use emretmrk/Qwen3.5-4B-TR-Finance with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use emretmrk/Qwen3.5-4B-TR-Finance with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "emretmrk/Qwen3.5-4B-TR-Finance"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emretmrk/Qwen3.5-4B-TR-Finance",
		"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/emretmrk/Qwen3.5-4B-TR-Finance

SGLang

How to use emretmrk/Qwen3.5-4B-TR-Finance 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 "emretmrk/Qwen3.5-4B-TR-Finance" \
    --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": "emretmrk/Qwen3.5-4B-TR-Finance",
		"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 "emretmrk/Qwen3.5-4B-TR-Finance" \
        --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": "emretmrk/Qwen3.5-4B-TR-Finance",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use emretmrk/Qwen3.5-4B-TR-Finance with Docker Model Runner:
```
docker model run hf.co/emretmrk/Qwen3.5-4B-TR-Finance
```

Qwen3.5-4B-TR-Finance

Qwen3.5-4B-TR-Finance is a Turkish and Turkish-finance adapted version of Qwen/Qwen3.5-4B.

The model was adapted in two sequential stages:

Domain-Adaptive / Continual Pre-training (DAPT)
Supervised Fine-Tuning (SFT)

Training focused on improving Turkish language capability, Turkish financial-domain knowledge, and Turkish instruction following.

This repository contains the standalone merged model weights obtained after merging the final LoRA adapter into the upstream model. It is the recommended repository for direct inference and benchmark / leaderboard submission.

Note: Training in this project used text-only Turkish and finance data. The upstream Qwen3.5-4B model is multimodal, but visual capabilities were not explicitly trained or evaluated in this adaptation.

Türkçe Özet

Bu model, Qwen/Qwen3.5-4B modelinin Türkçe dil yeteneğini ve özellikle Türkçe finans alanındaki bilgisini geliştirmek amacıyla iki aşamada eğitilmiştir:

DAPT / Continual Pre-training: Türkçe finans ve genel Türkçe ham metinleri
SFT: Türkçe finans soru-cevap / instruction verileri ve genel Türkçe instruction verileri

Bu repo, final LoRA adapter'ın ana modele merge edilmiş standalone model sürümüdür. Benchmark ve doğrudan inference için bu repo önerilir.

Model Details

Item	Value
Upstream model	`Qwen/Qwen3.5-4B`
Training language	Primarily Turkish
Domain	General Turkish + Finance
Training stages	DAPT → SFT
Fine-tuning method	LoRA / PEFT
LoRA target	`all-linear`
LoRA rank	`32`
LoRA alpha	`64`
LoRA dropout	`0.05`
Final artifact	Merged standalone weights
Main use	Turkish text generation, Turkish finance QA/instruction tasks, benchmarking

Training

Stage 1 — DAPT / Continual Pre-training

Datasets

Mixture

60% Turkish-finance text
40% general Turkish text

The 60/40 mixture was constructed on a sample/row basis, not by exact token count.

DAPT hyperparameters

Parameter	Value
Method	BF16/FP16 LoRA
Target modules	`all-linear`
Rank (`r`)	32
LoRA alpha	64
LoRA dropout	0.05
Learning rate	`5e-5`
Optimizer steps	1500
Max sequence length	2048
Packing	No
Gradient accumulation	16
LR scheduler	Cosine
Evaluation interval	100 steps
Checkpoint interval	250 steps

Stage 2 — Supervised Fine-Tuning

Datasets

SFT data strategy

All available examples from the two finance datasets were used after filtering.
Finance training examples were oversampled by approximately 3×.
Approximately 12k filtered examples from alpaca-gpt4-tr were used.
Evaluation examples were split before finance oversampling.
Samples exceeding the configured sequence-length budget were filtered.

SFT hyperparameters

Parameter	Value
Starting point	DAPT-trained LoRA adapter
Method	BF16/FP16 LoRA
Target modules	`all-linear`
Rank (`r`)	32
LoRA alpha	64
LoRA dropout	0.05
Learning rate	`1e-4`
Epochs	2
Max sequence length	2048
Packing	No
Loss	Completion-only
Gradient accumulation	16
LR scheduler	Cosine

Training Stack

Hugging Face Transformers
TRL
PEFT
Accelerate
Weights & Biases
TensorBoard

Usage

The upstream Qwen3.5-4B architecture is multimodal. The exact loading API should follow the config.json stored in this repository.

import torch
from transformers import AutoProcessor, AutoModelForMultimodalLM

MODEL_ID = "emretmrk/Qwen3.5-4B-TR-Finance"

processor = AutoProcessor.from_pretrained(MODEL_ID)

model = AutoModelForMultimodalLM.from_pretrained(
    MODEL_ID,
    torch_dtype="auto",
    device_map="auto",
)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Türkiye'de enflasyon ile politika faizi arasındaki ilişkiyi açıkla."
            }
        ],
    }
]

inputs = processor.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=256,
        do_sample=False,
    )

answer = processor.decode(
    outputs[0][inputs["input_ids"].shape[-1]:],
    skip_special_tokens=True,
)

print(answer)

Benchmark / Leaderboard Usage

For benchmark systems that request a Hugging Face model identifier, use this merged model repository:

emretmrk/Qwen3.5-4B-TR-Finance

The separate LoRA adapter repository is intended primarily for reproducibility, continued training, and PEFT-based loading.

Evaluation

Formal benchmark evaluation is performed separately from training.

Benchmark	Status
TurkBench	Pending
OpenLLMTurkishLeaderboard	Pending
Held-out Turkish Finance QA	Pending
Base vs DAPT vs DAPT+SFT comparison	Pending

Recommended comparison:

Qwen/Qwen3.5-4B
DAPT checkpoint / adapter
Final DAPT + SFT model

Intended Use

Turkish text generation
Turkish instruction following
Turkish finance-domain question answering
Turkish financial terminology and domain-language tasks
Research on continual pre-training, DAPT, LoRA, and SFT
Benchmarking Turkish language capability

Limitations

The model may generate incorrect or hallucinated information.
Financial knowledge can become outdated.
The model should not be treated as financial, investment, legal, or tax advice.
Training data may contain noise, inaccuracies, or biases inherited from upstream datasets.
The adaptation focused on text-only Turkish and finance data; multimodal capabilities were not explicitly optimized or evaluated.
Benchmark gains should not be assumed until independently measured.

License and Dataset Terms

The upstream Qwen/Qwen3.5-4B model is released under the Apache License 2.0.

This model was trained using third-party datasets. Their individual dataset cards and usage terms should be reviewed separately. Not every upstream dataset card exposes the same level of licensing detail. This repository's license metadata does not override any applicable terms associated with training data.

Acknowledgements

This work builds on:

Downloads last month: 91

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for emretmrk/Qwen3.5-4B-TR-Finance

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(730)

this model

emretmrk
/

Qwen3.5-4B-TR-Finance