Instructions to use alwaysgood/Qwen3.5_4B_ADS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alwaysgood/Qwen3.5_4B_ADS with Transformers:

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

pipe = pipeline("image-text-to-text", model="alwaysgood/Qwen3.5_4B_ADS")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("alwaysgood/Qwen3.5_4B_ADS")
model = AutoModelForMultimodalLM.from_pretrained("alwaysgood/Qwen3.5_4B_ADS", 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 = 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 Settings

llama.cpp

How to use alwaysgood/Qwen3.5_4B_ADS with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Use Docker

docker model run hf.co/alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

LM Studio
Jan

vLLM

How to use alwaysgood/Qwen3.5_4B_ADS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alwaysgood/Qwen3.5_4B_ADS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alwaysgood/Qwen3.5_4B_ADS",
		"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/alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

SGLang

How to use alwaysgood/Qwen3.5_4B_ADS 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 "alwaysgood/Qwen3.5_4B_ADS" \
    --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": "alwaysgood/Qwen3.5_4B_ADS",
		"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 "alwaysgood/Qwen3.5_4B_ADS" \
        --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": "alwaysgood/Qwen3.5_4B_ADS",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use alwaysgood/Qwen3.5_4B_ADS with Ollama:
```
ollama run hf.co/alwaysgood/Qwen3.5_4B_ADS:Q4_K_M
```

Unsloth Studio

How to use alwaysgood/Qwen3.5_4B_ADS 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 alwaysgood/Qwen3.5_4B_ADS 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 alwaysgood/Qwen3.5_4B_ADS to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for alwaysgood/Qwen3.5_4B_ADS to start chatting

How to use alwaysgood/Qwen3.5_4B_ADS with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "alwaysgood/Qwen3.5_4B_ADS:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use alwaysgood/Qwen3.5_4B_ADS with Docker Model Runner:
```
docker model run hf.co/alwaysgood/Qwen3.5_4B_ADS:Q4_K_M
```

Lemonade

How to use alwaysgood/Qwen3.5_4B_ADS with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5_4B_ADS-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use alwaysgood/Qwen3.5_4B_ADS with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use alwaysgood/Qwen3.5_4B_ADS with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf alwaysgood/Qwen3.5_4B_ADS:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "alwaysgood/Qwen3.5_4B_ADS:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Qwen3.5_4B_ADS

Qwen3.5_4B_ADS is a full fine-tune of unsloth/Qwen3.5-4B for English-to-Korean financial translation. It was trained with the DQS low-QE curriculum using seed 42.

This repository contains both the original Transformers checkpoint and one LM Studio/llama.cpp export:

model.safetensors: original BF16 fine-tuned checkpoint
Qwen3.5_4B_ADS-Q4_K_M.gguf: the only quantized main-model variant
mmproj-Qwen3.5_4B_ADS-BF16.gguf: vision encoder/projector companion

The BF16 mmproj is not an additional LLM quantization variant. It is kept at BF16 for multimodal compatibility and quality.

LM Studio

Use the latest LM Studio runtime and download the Q4_K_M variant:

lms get https://huggingface.co/alwaysgood/Qwen3.5_4B_ADS@Q4_K_M

The matching mmproj file enables image input. For translation, disable thinking and ask for translation-only output, for example:

Translate the following English financial text into Korean. Return only the translation.

<source text>

Training and provenance

Tuning: full-parameter supervised fine-tuning
Seed: 42
Selection: low quality-estimation score first (qe_selection_order=low)
Base model thinking during training/evaluation: disabled
Vision layers: not trained; the base model's multimodal components were preserved
Run artifacts: qwen35_4b_it_full_lowqe_seed42
Source revision: fa8166a883d96460cc285b46d66b74a074b4b8d4

The checkpoint does not contain the optional Qwen3.5 MTP auxiliary head even though the inherited config declares one. The GGUF export therefore excludes MTP. Normal autoregressive generation is unaffected; MTP speculative decoding is not provided.

Evaluation

The following scores are from the original BF16 final checkpoint on the 500-row held-out test set. They are not claimed as a separate Q4_K_M evaluation.

Metric	Score
BLEU	27.4731
chrF	47.9918
COMET (`wmt22-comet-da`)	0.8906
COMETKiwi (`wmt22-cometkiwi-da`)	0.8565
XCOMET-XXL	0.8675
MetricX-24 Hybrid XXL (lower is better)	3.8712

Full evaluation records and configuration are available in the linked run.

License and data note

The model weights follow the Apache-2.0 license of the base model. The training corpus aggregates sources with mixed upstream terms; the dataset card is marked license: other. Users are responsible for reviewing the source-specific terms described in alwaysgood/financial-english-source-corpus.

Downloads last month: 57

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for alwaysgood/Qwen3.5_4B_ADS

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

unsloth/Qwen3.5-4B

Finetuned

(228)

this model

alwaysgood
/

Qwen3.5_4B_ADS

Qwen3.5_4B_ADS

LM Studio

Training and provenance

Evaluation

License and data note

Model tree for alwaysgood/Qwen3.5_4B_ADS

Datasets used to train alwaysgood/Qwen3.5_4B_ADS