This model is fine-tuned on the Hamid-reza/Adv-small-persian-QA dataset using the LoRA method. The base model is the qwen2.5 3b instruct model. This model answers general user questions.
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: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]
Uses
The goal of this model is to answer some common questions from users.
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
Training Details
Training Data
Hamid-reza/Adv-small-persian-QA
[More Information Needed]
Training Procedure
This model is fine-tuned using the LoRA method with rank 4 and its epoch is set to 27.
task_type = TaskType.CAUSAL_LM,
target_modules = ["q_proj", "k_proj", "v_proj"]
Training regime: [More Information Needed]
num_train_epochs = 27,
learning_rate = 0.001,
logging_steps = 100,
report_to = "tensorboard"
Speeds, Sizes, Times [optional]
4266/4266 1:17:27, Epoch 27/27
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
زنبور های عسل چگونه عسل تولید می کنند؟
کار را با گردآوری شهد گلها در کندو انجام میدهد
[More Information Needed]
Summary
The Qwen2.5 3b Instruct model was fine-tuned using the LoRA method on the Hamid-reza/Adv-small-persian-QA dataset, and the fine-tuning time was 1 hour and 17 minutes. The last reported loss value was 0.03, and it was able to answer the questions correctly, but given that the number of data was small, it did not give accurate answers to questions with similar structures.
