Instructions to use altomek/Lo101-3B-AnD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use altomek/Lo101-3B-AnD with Transformers:

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

pipe = pipeline("text-generation", model="altomek/Lo101-3B-AnD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("altomek/Lo101-3B-AnD")
model = AutoModelForCausalLM.from_pretrained("altomek/Lo101-3B-AnD")
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 altomek/Lo101-3B-AnD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "altomek/Lo101-3B-AnD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "altomek/Lo101-3B-AnD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/altomek/Lo101-3B-AnD

SGLang

How to use altomek/Lo101-3B-AnD 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 "altomek/Lo101-3B-AnD" \
    --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": "altomek/Lo101-3B-AnD",
		"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 "altomek/Lo101-3B-AnD" \
        --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": "altomek/Lo101-3B-AnD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use altomek/Lo101-3B-AnD with Docker Model Runner:
```
docker model run hf.co/altomek/Lo101-3B-AnD
```

intro music...

This is...

Llama Lo1 01

My first RP directed finetune and merge! Not as expresive like Llama Instruct might be. Writes simpler responses in chat. Somewhat broken... I need to learn more about chat templates... ;P

Trained on few datasets from jeiku - Thank you!

Have fun!

Settings

ChatML, Alpaca or Llama 3 Instruct templates for chat should work, however model have dificulties with longer responses so make sure to set response tokens to something like 256!
Set Temperature below 1
You can easily overload this AI with too complicaded, long character cards. Keep things simple! ;P

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

F16

Model tree for altomek/Lo101-3B-AnD

IntervitensInc/Llama-3.2-3B-chatml

alpindale/Llama-3.2-3B-Instruct

Merge model

this model

Collection including altomek/Lo101-3B-AnD

My models

Collection

6 items • Updated Mar 2