Instructions to use Aculi/Llama-3.2-3B-SmartBoi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aculi/Llama-3.2-3B-SmartBoi with Transformers:

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

pipe = pipeline("text-generation", model="Aculi/Llama-3.2-3B-SmartBoi")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aculi/Llama-3.2-3B-SmartBoi")
model = AutoModelForCausalLM.from_pretrained("Aculi/Llama-3.2-3B-SmartBoi")
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 Aculi/Llama-3.2-3B-SmartBoi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aculi/Llama-3.2-3B-SmartBoi"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aculi/Llama-3.2-3B-SmartBoi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aculi/Llama-3.2-3B-SmartBoi

SGLang

How to use Aculi/Llama-3.2-3B-SmartBoi 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 "Aculi/Llama-3.2-3B-SmartBoi" \
    --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": "Aculi/Llama-3.2-3B-SmartBoi",
		"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 "Aculi/Llama-3.2-3B-SmartBoi" \
        --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": "Aculi/Llama-3.2-3B-SmartBoi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aculi/Llama-3.2-3B-SmartBoi with Docker Model Runner:
```
docker model run hf.co/Aculi/Llama-3.2-3B-SmartBoi
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3.2-3B-SmartBoi

This is a finetune to include 'thinking' tags (plus others).

It makes this model a lot smarter (at least in maths), alltho the tags are only used in english somehow.

This model has not been made uncensored.

$maths.jpg$

Prompt Template

This Model uses Llama-3 Chat:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

This is text

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Finetune Info:

The following YAML configuration was used to finetune this model:

base_model: alpindale/Llama-3.2-3B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: true
strict: false

chat_template: llama3
datasets:
  - path: Fischerboot/small-boi-thinkin
    type: sharegpt
    conversation: llama3
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./outputs/yuh

adapter: qlora
lora_model_dir:

sequence_len: 4096
sample_packing: false
pad_to_sequence_len: true

lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

loss_watchdog_threshold: 8.0
loss_watchdog_patience: 3

eval_sample_packing: false
warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|begin_of_text|>"
  eos_token: "<|end_of_text|>"
  pad_token: "<|end_of_text|>"

Training results:

Training Loss	Epoch	Step	Validation Loss
1.5032	0.0000	1	1.6556
1.2011	0.5000	10553	0.6682

Downloads last month: 2

Safetensors

Model size

3B params

Tensor type

F16

Model tree for Aculi/Llama-3.2-3B-SmartBoi

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

(1602)

this model

Quantizations

3 models

Aculi
/

Llama-3.2-3B-SmartBoi

Llama-3.2-3B-SmartBoi

Prompt Template

Finetune Info:

Training results:

Model tree for Aculi/Llama-3.2-3B-SmartBoi

Dataset used to train Aculi/Llama-3.2-3B-SmartBoi