Instructions to use TitleOS/Linden-4B-FP32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TitleOS/Linden-4B-FP32 with Transformers:

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

pipe = pipeline("text-generation", model="TitleOS/Linden-4B-FP32")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TitleOS/Linden-4B-FP32")
model = AutoModelForCausalLM.from_pretrained("TitleOS/Linden-4B-FP32")
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

vLLM

How to use TitleOS/Linden-4B-FP32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TitleOS/Linden-4B-FP32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TitleOS/Linden-4B-FP32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TitleOS/Linden-4B-FP32

SGLang

How to use TitleOS/Linden-4B-FP32 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 "TitleOS/Linden-4B-FP32" \
    --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": "TitleOS/Linden-4B-FP32",
		"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 "TitleOS/Linden-4B-FP32" \
        --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": "TitleOS/Linden-4B-FP32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TitleOS/Linden-4B-FP32 with Docker Model Runner:
```
docker model run hf.co/TitleOS/Linden-4B-FP32
```

TitleOS commited on 12 days ago

Commit

e4dfc4d

verified ·

1 Parent(s): 7e9193c

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -0

README.md CHANGED Viewed

@@ -230,6 +230,21 @@ fills with live MPR headlines just before playback.
 LoRA fine-tune on [TitleOS/Linden_MN_DJ_Persona](https://huggingface.co/datasets/TitleOS/Linden_MN_DJ_Persona), a synthetic dataset of Linden-style segments, featuring weather, news and commentary on songs generated by Gemini-3-Flash. The merged checkpoint is
 the adapter applied to `Qwen/Qwen3.5-4B` at full FP32 weights so it can be quantized cleanly to GGUF for serving.
 ---
 ## License

 LoRA fine-tune on [TitleOS/Linden_MN_DJ_Persona](https://huggingface.co/datasets/TitleOS/Linden_MN_DJ_Persona), a synthetic dataset of Linden-style segments, featuring weather, news and commentary on songs generated by Gemini-3-Flash. The merged checkpoint is
 the adapter applied to `Qwen/Qwen3.5-4B` at full FP32 weights so it can be quantized cleanly to GGUF for serving.
+```
+base_model: Qwen/Qwen3.5-4B
+method: RS-LoRA
+lora_r: 64
+lora_alpha: 64
+lora_target: all linear layers
+epochs: 2
+learning_rate: 2e-4
+batch_size: 2
+max_seq_len: 2048
+dataset_format: sharegpt
+```
+Trained on a Tesla P40 over 5 hours.
 ---
 ## License