Instructions to use MRAIRR/minillama3_8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MRAIRR/minillama3_8b with Transformers:

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

pipe = pipeline("text-generation", model="MRAIRR/minillama3_8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MRAIRR/minillama3_8b")
model = AutoModelForCausalLM.from_pretrained("MRAIRR/minillama3_8b")
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 MRAIRR/minillama3_8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MRAIRR/minillama3_8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MRAIRR/minillama3_8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MRAIRR/minillama3_8b

SGLang

How to use MRAIRR/minillama3_8b 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 "MRAIRR/minillama3_8b" \
    --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": "MRAIRR/minillama3_8b",
		"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 "MRAIRR/minillama3_8b" \
        --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": "MRAIRR/minillama3_8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MRAIRR/minillama3_8b with Docker Model Runner:
```
docker model run hf.co/MRAIRR/minillama3_8b
```

Train Config

base_model: allganize/Llama-3-Alpha-Ko-8B-Instruct model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer

load_in_8bit: false load_in_4bit: true strict: false

datasets:

path: ? type: alpaca dataset_prepared_path: val_set_size: 0 output_dir: ./outputs/qlora-out

adapter: qlora lora_model_dir:

sequence_len: 2048 sample_packing: true pad_to_sequence_len: true

lora_r: 32 lora_alpha: 16 lora_dropout: 0.05 lora_target_modules:

q_proj
v_proj

lora_target_linear: true lora_fan_in_fan_out: lora_modules_to_save:

embed_tokens
lm_head

wandb_project: wandb_entity: wandb_watch: wandb_name: wandb_log_model:

gradient_accumulation_steps: 4 micro_batch_size: 2 num_epochs: 3 optimizer: paged_adamw_32bit 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: 100 xformers_attention: flash_attention: true

warmup_steps: 10 evals_per_epoch: 4 eval_table_size: saves_per_epoch: 1 debug: deepspeed: weight_decay: 0.01 neftune_noise_alpha: 5 fsdp: fsdp_config: special_tokens: pad_token: :"<|end_of_text|>"

Downloads last month: 11