Instructions to use kieraisverybored/fein with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kieraisverybored/fein with Transformers:

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

pipe = pipeline("text-generation", model="kieraisverybored/fein")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kieraisverybored/fein")
model = AutoModelForCausalLM.from_pretrained("kieraisverybored/fein")
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 kieraisverybored/fein with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kieraisverybored/fein

SGLang

How to use kieraisverybored/fein 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 "kieraisverybored/fein" \
    --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": "kieraisverybored/fein",
		"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 "kieraisverybored/fein" \
        --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": "kieraisverybored/fein",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kieraisverybored/fein with Docker Model Runner:
```
docker model run hf.co/kieraisverybored/fein
```

fein-14B 🚀

Finetuned Qwen 3-14B on the Smol-Talk Dolphin dataset
with LoRA adapters, then merged into a single set of full-precision weights for easy inference.

Model	Params	Base	Quant options	Checkpoints
`fein-14b`	14.8 B	– (merged)	4-bit / 8-bit	one folder, ready to load

Quick start (inference)
Installation
Training
Continuing training
Merging the adapters
Pushing to your HF space
Repo layout
Citation
License

Quick start (inference)

git clone https://huggingface.co/kieraisverybored/fein
cd fein

# Optional: create & activate conda env
conda create -n fein python=3.11 -y
conda activate fein

Now install requirements.

# 4-bit streaming chat
python infer.py --model .

# short answers (128 tokens max)
python infer.py --model . --max-new 128

Sample session

User: Hi!
Assistant: Hello! How can I assist you today? 😊

Installation

# Core libs
pip install torch>=2.2.0 transformers>=4.40.0 accelerate bitsandbytes
# Optional quality-of-life
pip install tqdm rich

GPU: A single 24 GB card is enough for 4-bit inference. CPU: Possible with 8-bit + device_map="cpu", but sloooow.

Citation

@misc{fein2025,
  title       = {FEIN–14B: Smol-Talk fine-tune of Qwen 3-14B},
  author      = {KieraDev},
  year        = {2025},
  howpublished= {\url{https://huggingface.co/kieraisverybored/fein}}
}

License

The base model inherits the Apache License; the finetuned weights are released under the same terms. The dataset is MIT-licensed. See for full details.

Have fun experimenting—and please open an issue if you hit a snag! 🙌

Downloads last month: 1

Safetensors

Model size

15B params

Tensor type

F16

Model tree for kieraisverybored/fein

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

(260)

this model

kieraisverybored
/

fein