Waktaverse-Llama-3-KO-8B-Instruct Model Card
Model Details
Waktaverse-Llama-3-KO-8B-Instruct is a Korean language model developed by Waktaverse AI team. This large language model is a specialized version of the Meta-Llama-3-8B-Instruct, tailored for Korean natural language processing tasks. It is designed to handle a variety of complex instructions and generate coherent, contextually appropriate responses.
- Developed by: Waktaverse AI
- Model type: Large Language Model
- Language(s) (NLP): Korean, English
- License: Llama3
- Finetuned from model: meta-llama/Meta-Llama-3-8B-Instruct
Model Sources
- Repository: GitHub
- Paper : [More Information Needed]
Uses
Direct Use
The model can be utilized directly for tasks such as text completion, summarization, and question answering without any fine-tuning.
Out-of-Scope Use
This model is not intended for use in scenarios that involve high-stakes decision-making including medical, legal, or safety-critical areas due to the potential risks of relying on automated decision-making. Moreover, any attempt to deploy the model in a manner that infringes upon privacy rights or facilitates biased decision-making is strongly discouraged.
Bias, Risks, and Limitations
While Waktaverse Llama 3 is a robust model, it shares common limitations associated with machine learning models including potential biases in training data, vulnerability to adversarial attacks, and unpredictable behavior under edge cases. There is also a risk of cultural and contextual misunderstanding, particularly when the model is applied to languages and contexts it was not specifically trained on.
How to Get Started with the Model
You can run conversational inference using the Transformers Auto classes. We highly recommend that you add Korean system prompt for better output. Adjust the hyperparameters as you need.
Example Usage
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
device = (
"cuda:0" if torch.cuda.is_available() else # Nvidia GPU
"mps" if torch.backends.mps.is_available() else # Apple Silicon GPU
"cpu"
)
model_id = "PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map=device,
)
################################################################################
# Generation parameters
################################################################################
num_return_sequences=1
max_new_tokens=1024
temperature=0.6
top_p=0.9
repetition_penalty=1.1
def prompt_template(system, user):
return (
"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n"
f"{system}<|eot_id|>"
"<|start_header_id|>user<|end_header_id|>\n\n"
f"{user}<|eot_id|>"
"<|start_header_id|>assistant<|end_header_id|>\n\n"
)
def generate_response(system ,user):
prompt = prompt_template(system, user)
input_ids = tokenizer.encode(
prompt,
add_special_tokens=False,
return_tensors="pt"
).to(device)
outputs = model.generate(
input_ids=input_ids,
pad_token_id=tokenizer.eos_token_id,
num_return_sequences=num_return_sequences,
max_new_tokens=max_new_tokens,
do_sample=True,
temperature=temperature,
top_p=top_p,
repetition_penalty=repetition_penalty
)
return tokenizer.decode(outputs[0], skip_special_tokens=False)
system_prompt = "λ€μ μ§μμ¬νμ λν μλ΅μ μμ±ν΄μ£ΌμΈμ."
user_prompt = "νΌλ³΄λμΉ μμ΄μ λν΄ μ€λͺ
ν΄μ£ΌμΈμ."
response = generate_response(system_prompt, user_prompt)
print(response)
Example Output
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
λ€μ μ§μμ¬νμ λν μλ΅μ μμ±ν΄ μ£ΌμΈμ.<|eot_id|><|start_header_id|>user<|end_header_id|>
νΌλ³΄λμΉ μμ΄μ λν΄ μ€λͺ
ν΄μ£ΌμΈμ.<|eot_id|><|start_header_id|>assistant<|end_header_id|>
νΌλ³΄λμΉ μμ΄μ μνμμ μμ£Ό μ¬μ©λλ μμ΄ μ€ νλλ‘, 0κ³Ό 1λ‘ μμνμ¬ λ€μ νμ΄ μ΄μ λ νμ ν©μΌλ‘ ꡬμ±λ©λλ€. νΌλ³΄λμΉ μμ΄μ μ λͺ
ν μνμ λ μ¨ μλ μ°λλ‘λΉμΉ νΌλ³΄λμΉκ° μ μνμΌλ©°, κ·Έμ μ΄λ¦μ λ°μ λͺ
λͺ
λμμ΅λλ€. μ΄ μμ΄μ μμ°μμ μ μλ₯Ό ν¬ν¨νλ©°, κ° νμ μ΄μ λ νμ ν©μ
λλ€. μλ₯Ό λ€μ΄, 첫 λ²μ§Έ νμ 0μ΄κ³ λ λ²μ§Έ νμ 1μ΄λ©°, μΈ λ²μ§Έ νμ 2μ΄κ³ λ€ λ²μ§Έ νμ 3μ
λλ€. νΌλ³΄λμΉ μμ΄μ μμ°¨μ μΌλ‘ μ¦κ°νλ νΉμ§μ΄ μμ§λ§, μ«μκ° μ»€μ§μλ‘ μ μ λ λΉ λ₯΄κ² μ¦κ°ν©λλ€. νΌλ³΄λμΉ μμ΄μ λ€μν λΆμΌμμ μ¬μ©λλ©°, μν, μ»΄ν¨ν° κ³Όν, μλ¬Όν λ±μμ μ€μν μν μ ν©λλ€.<|eot_id|>
Training Details
Training Data
The model is trained on the MarkrAI/KoCommercial-Dataset, which consists of various commercial texts in Korean.
Training Procedure
The model training used LoRA for computational efficiency. 0.04 billion parameters(0.51% of total parameters) were trained.
Training Hyperparameters
################################################################################
# bitsandbytes parameters
################################################################################
load_in_4bit=True
bnb_4bit_compute_dtype=torch.bfloat16
bnb_4bit_quant_type="nf4"
bnb_4bit_use_double_quant=True
################################################################################
# LoRA parameters
################################################################################
task_type="CAUSAL_LM"
target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"]
r=8
lora_alpha=16
lora_dropout=0.05
bias="none"
################################################################################
# TrainingArguments parameters
################################################################################
num_train_epochs=1
per_device_train_batch_size=1
gradient_accumulation_steps=1
gradient_checkpointing=True
learning_rate=2e-5
lr_scheduler_type="cosine"
warmup_ratio=0.1
optim = "paged_adamw_32bit"
weight_decay=0.01
################################################################################
# SFT parameters
################################################################################
max_seq_length=4096
packing=False
Evaluation
Metrics
- Ko-HellaSwag:
- Ko-MMLU:
- Ko-Arc:
- Ko-Truthful QA:
- Ko-CommonGen V2:
Results
Benchmark | Waktaverse Llama 3 8B | Llama 3 8B |
Ko-HellaSwag: | 0 | 0 |
Ko-MMLU: | 0 | 0 |
Ko-Arc: | 0 | 0 |
Ko-Truthful QA: | 0 | 0 |
Ko-CommonGen V2: | 0 | 0 |
Technical Specifications
Compute Infrastructure
Hardware
- GPU: NVIDIA GeForce RTX 4080 SUPER
Software
- Operating System: Linux
- Deep Learning Framework: Hugging Face Transformers, PyTorch
Training Details
- Training time: 80 hours
- More details on Weights & Biases
Citation
Waktaverse-Llama-3
@article{waktaversellama3modelcard,
title={Waktaverse Llama 3 Model Card},
author={AI@Waktaverse},
year={2024},
url = {https://huggingface.co/PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct}
Llama-3
@article{llama3modelcard,
title={Llama 3 Model Card},
author={AI@Meta},
year={2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
Model Card Authors
- Downloads last month
- 1,490
Model tree for PathFinderKR/Waktaverse-Llama-3-KO-8B-Instruct
Base model
meta-llama/Meta-Llama-3-8B-Instruct