DAIS-Qwen3-8B-qdora

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: SIQRIT
• Model type : Qwen/Qwen3-8B
• Language(s) (NLP) : Korean-based Learning
• License : apache-2.0
• Finetuned from model : Q-DoRA

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository : [GitHub]

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

The Vector DB used in the training of this model was created based on YouTube scripts. In addition, the YouTube script used the automatic translation generation function. Therefore, for Vector DB references, there is no problem with sentence generation, but word can sometimes be incomplete.

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Special tokens have been added to enhance prompt engineering. The hyperparameters reflecting the current latest paper trends are described in detail below.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

YouTube Scripts on Korean-Based Science

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

<!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

• Special Tokens

  special_tokens_dict = { "additional_special_tokens": [ "[DAIS_INSTRUCTION]", "[DAIS_STYLE]", "[DAIS_RULE]", "[DAIS_EXAMPLE]", "[HISTORY]", "[INPUT]", "[OUTPUT]", "[CONTEXT]" ] }

• DoRA Adapter Config

  lora_config = LoraConfig( r=64, lora_alpha=32, target_modules=[ "model.embed_tokens", "q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj" ], lora_dropout=0.05, bias="none", task_type="CAUSAL_LM", use_dora=True )

• Training Arguments

  training_args = TrainingArguments( output_dir=OUTPUT_DIR, per_device_train_batch_size=4, per_device_eval_batch_size=4, gradient_accumulation_steps=8, optim="paged_adamw_32bit", gradient_checkpointing=True, num_train_epochs=20, learning_rate=3e-5, lr_scheduler_type="cosine", warmup_ratio=0.1, eval_strategy="epoch", save_strategy="epoch", save_total_limit=5, load_best_model_at_end=True, metric_for_best_model="eval_loss", greater_is_better=False, logging_steps=10, weight_decay=0.01, max_grad_norm=1.0, bf16=True, fp16=False, group_by_length=True, remove_unused_columns=True, push_to_hub=False, report_to="none" )

• Supervised Fine-Tuning

  trainer = SFTTrainer( model=model, args=training_args, train_dataset=train_dataset, eval_dataset=eval_dataset, peft_config=lora_config, callbacks=[EarlyStoppingCallback(early_stopping_patience=5)] )

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

This model is named DAIS and its official name is Divergent AI with Science. Also it is trained on Korean and aims to train on the subject of a science AI influencer.

Compute Infrastructure

[More Information Needed]

Hardware

RunPod A100 100GB(DISK)/100GB(Container)

Software

runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

SIQRIT

Model Card Contact

[email protected]