Instructions to use MRAIRR/minillama3_8b_all with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MRAIRR/minillama3_8b_all with Transformers:

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

pipe = pipeline("text-generation", model="MRAIRR/minillama3_8b_all")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MRAIRR/minillama3_8b_all")
model = AutoModelForCausalLM.from_pretrained("MRAIRR/minillama3_8b_all")
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_all with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MRAIRR/minillama3_8b_all"
# 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_all",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MRAIRR/minillama3_8b_all

SGLang

How to use MRAIRR/minillama3_8b_all 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_all" \
    --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_all",
		"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_all" \
        --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_all",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MRAIRR/minillama3_8b_all with Docker Model Runner:
```
docker model run hf.co/MRAIRR/minillama3_8b_all
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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

HOW TO USE

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "MRAIRR/minillama3_8b_all"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

PROMPT_TEMPLATE = """
# 지시:
당신은 인공지능 어시스턴트입니다. 사용자가 묻는 말에 친절하고 정확하게 답변하세요.
"""

messages = [
    {"role": "system", "content":PROMPT_TEMPLATE},
    {"role": "user", "content": "안녕? 내 이름은 현수 ㅎㅎ 만나서 반가워"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    temperature = 0.3,
    eos_token_id=terminators,
    do_sample=True,
    repetition_penalty=1.05,
)
response = outputs[0][input_ids.shape[-1]:]
response_text = tokenizer.decode(response, skip_special_tokens=True)
completion = '\n'.join(response_text.split("."))
print(completion)

Downloads last month: 11

Model tree for MRAIRR/minillama3_8b_all

Quantizations

1 model

MRAIRR
/

minillama3_8b_all

HOW TO USE

Model tree for MRAIRR/minillama3_8b_all

Space using MRAIRR/minillama3_8b_all 1