Instructions to use techwithsergiu/Qwen3.5-text-9B-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use techwithsergiu/Qwen3.5-text-9B-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="techwithsergiu/Qwen3.5-text-9B-bnb-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("techwithsergiu/Qwen3.5-text-9B-bnb-4bit")
model = AutoModelForCausalLM.from_pretrained("techwithsergiu/Qwen3.5-text-9B-bnb-4bit", device_map="auto")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use techwithsergiu/Qwen3.5-text-9B-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "techwithsergiu/Qwen3.5-text-9B-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "techwithsergiu/Qwen3.5-text-9B-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/techwithsergiu/Qwen3.5-text-9B-bnb-4bit

SGLang

How to use techwithsergiu/Qwen3.5-text-9B-bnb-4bit 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 "techwithsergiu/Qwen3.5-text-9B-bnb-4bit" \
    --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": "techwithsergiu/Qwen3.5-text-9B-bnb-4bit",
		"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 "techwithsergiu/Qwen3.5-text-9B-bnb-4bit" \
        --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": "techwithsergiu/Qwen3.5-text-9B-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use techwithsergiu/Qwen3.5-text-9B-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/techwithsergiu/Qwen3.5-text-9B-bnb-4bit
```

techwithsergiu commited on Mar 13

Commit

33aa419

verified ·

1 Parent(s): 9eef1d1

docs: replace TBD fine-tuning section with qwen-qlora-train quick start

Browse files

Files changed (2) hide show

README.md +25 -9
diagrams/diagram_02.png +2 -2

README.md CHANGED Viewed

@@ -92,15 +92,31 @@ print(response)
 ## Fine-tuning
-> **TBD** — LoRA training with this model has not been documented yet.
-> The model has been verified for inference (text generation, thinking ON/OFF).
-> The expectation is that standard Unsloth LoRA training applies — this is a
-> text-only BNB 4-bit model architecturally identical to models Unsloth supports —
-> but this has not been tested yet and there is no official Qwen3.5 text-only
-> training guide to reference.
->
-> For VLM (image + text) fine-tuning of the full model, see:
-> [unsloth.ai/docs/models/qwen3.5/fine-tune](https://unsloth.ai/docs/models/qwen3.5/fine-tune)
 ## Pipeline diagram

 ## Fine-tuning
+This is the **primary training target** for text LoRA fine-tuning.
+Training pipeline: **[github.com/techwithsergiu/qwen-qlora-train](https://github.com/techwithsergiu/qwen-qlora-train)**
+QLoRA (Unsloth + TRL + PEFT) · rank 16–64 · validated on RTX 3070 8 GB
+```bash
+# Quick start — install
+pip install "unsloth[cu124-torch260] @ git+https://github.com/unslothai/unsloth.git"
+pip install git+https://github.com/techwithsergiu/qwen-qlora-train.git
+# Train with a ready-made config
+qlora-train configs/qwen35/0.8b.yaml   # or 2b / 4b
+```
+After training, test the adapter without merging:
+```bash
+qlora-infer \
+  --model   techwithsergiu/Qwen3.5-text-9B-bnb-4bit \
+  --adapter adapters/<run_name>
+```
+For VLM (image + text) fine-tuning of the full model, see:
+[unsloth.ai/docs/models/qwen3.5/fine-tune](https://unsloth.ai/docs/models/qwen3.5/fine-tune)
 ## Pipeline diagram

diagrams/diagram_02.png CHANGED Viewed

Git LFS Details

SHA256: b9f3c328651ec80260c9b99aa18b04b8170456b19fc45fa695695111660e7772
Pointer size: 131 Bytes
Size of remote file: 163 kB

Git LFS Details

SHA256: b36a960394a728037ced0c1a32ef6066c345e46087aaa0dacc563cd26a17840b
Pointer size: 131 Bytes
Size of remote file: 181 kB