Instructions to use Oysiyl/qwen3-1.7b-unslop-good-lora-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Oysiyl/qwen3-1.7b-unslop-good-lora-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Oysiyl/qwen3-1.7b-unslop-good-lora-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Oysiyl/qwen3-1.7b-unslop-good-lora-v1")
model = AutoModelForCausalLM.from_pretrained("Oysiyl/qwen3-1.7b-unslop-good-lora-v1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Oysiyl/qwen3-1.7b-unslop-good-lora-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Oysiyl/qwen3-1.7b-unslop-good-lora-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Oysiyl/qwen3-1.7b-unslop-good-lora-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Oysiyl/qwen3-1.7b-unslop-good-lora-v1

SGLang

How to use Oysiyl/qwen3-1.7b-unslop-good-lora-v1 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 "Oysiyl/qwen3-1.7b-unslop-good-lora-v1" \
    --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": "Oysiyl/qwen3-1.7b-unslop-good-lora-v1",
		"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 "Oysiyl/qwen3-1.7b-unslop-good-lora-v1" \
        --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": "Oysiyl/qwen3-1.7b-unslop-good-lora-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Oysiyl/qwen3-1.7b-unslop-good-lora-v1 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 Oysiyl/qwen3-1.7b-unslop-good-lora-v1 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 Oysiyl/qwen3-1.7b-unslop-good-lora-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Oysiyl/qwen3-1.7b-unslop-good-lora-v1 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Oysiyl/qwen3-1.7b-unslop-good-lora-v1",
    max_seq_length=2048,
)

Docker Model Runner
How to use Oysiyl/qwen3-1.7b-unslop-good-lora-v1 with Docker Model Runner:
```
docker model run hf.co/Oysiyl/qwen3-1.7b-unslop-good-lora-v1
```

Oysiyl commited on Mar 25

Commit

60138ee

verified ·

1 Parent(s): 7c0e325

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +34 -4

README.md CHANGED Viewed

@@ -82,13 +82,43 @@ Use this full fiction passage for held-out testing:
 > She stepped forward.
 > The mountain exhaled.
-## Observed output on that sample
-The 1.7B model is more fluent than the 0.6B version, but it still drifts hard away from the task and turns the passage into a different scene.
-Excerpt from the observed output:
-> A sudden gust roared through the valley ... “She can't escape me,” he warned ... “Then it seems you must make your choice now,” he added ... They journeyed deeper, where the night enveloped them ...
 ## Judgment

 > She stepped forward.
 > The mountain exhaled.
+## Full observed output on that sample
+```text
+A sudden gust roared through the valley, and the earth seemed to sigh with relief. At the pass, she paused, wrapped in a dress that fluttered like a flag of distress; behind her, the sky burst open, flames spilling from the heavens. She looked upon the dying glows of the hills, which were quickly fading into darkness, each light vanishing with an eerie precision. Just beyond lay the mournful sound of church bells, ringing solemnly. All around, signs of despair appeared, yet she remained resolute.
+“She can't escape me,” he warned, his voice trembling. “When she crosses that boundary, no return will be possible.”
+“I know,” she replied quietly. “But I won’t run.”
+The ground trembled as thunder echoed, sending a deep rumble through the mountains.
+“Then it seems you must make your choice now,” he added, urgency lacing his tone. “You can either stand by or flee.”
+She turned toward him. “I choose to stay. But do remember: this was not your decision.”
+He caught her hand, squeezing it tightly before stepping away. “Your choice was yours alone. Now it's mine to take action.”
+With that, they moved on, crossing the valley beneath a heavy, ominous cloud.
+As they pressed onward, a chill washed over them, filling their lungs with its sharp bite.
+“The mountain has inhaled,” someone murmured beside her.
+“What does that mean?” she asked, curiosity piqued.
+“It means it is about to exhale,” another responded, a sense of foreboding settling within the air.
+They journeyed deeper, where the night enveloped them, and soon they entered a realm thick with mist.
+At dawn, they emerged, finding themselves surrounded by a breathtaking landscape. A massive forest stretched out, lush trees standing majestically under a golden sun. As they advanced, the sun dimmed, revealing a vast plain dotted with towering grasslands stretching toward the horizon.
+Their path led them to a cliff overlooking a river shimmering with the gentle glow of morning light. There stood a small house nestled among the trees, resembling a quaint cottage, though it held little warmth. Nearby, two figures stood, waiting anxiously for her arrival.
+One was a young boy, while the other appeared older, likely the father figure. He wore a red robe, and his beard bristled with white as he regarded her with concern.
+“How are you faring?” he questioned, his voice steady
+```
 ## Judgment