NGILlama3-merged

NGI_LLama3_8b

Model Description

Model Description: unsloth/llama-3-8b-bnb-4bit

Model Card Title

NGI_LLama3_8b

Tags

• text-generation-inference
• transformers
• unsloth
• llama
• trl

Model Type

text-generation

---

Model Details

Dataset: Custom News dataset

Training Data Source: [Please provide the source]

Training Data Size: 840,000

Number of Training Steps: 210,000

Model Architecture: LLaMA

---

Technical Specifications

Framework: PyTorch

Hyperparameters:

• Learning Rate: 5e-5
• Batch Size: 4
• Optimizer: adamw_8bit

Evaluation Metrics:

• Metric Name: [Accuracy]
• Score: [0.9981]
• Metric Name: [F1 score]
• Score: [0.9980]
• Metric Name: [Precision]
• Score: [0.9963]
• Metric Name: [Recall]
• Score: [0.9996]

Hardware Used:

• Number of GPUs/CPUs: 1 GPU
• Type of GPUs/CPUs: [NVIDIA RTX A4000 ]

Training Duration: [24 days]

---

Usage

Intended Use Cases: [Please provide the use cases]

Example Input: [Please provide an example input]

Example Output: [Please provide an example output]

---

Licensing and Access

License Type: [apache-2.0]

Model Access: [Public/Private]

---

Additional Information

Contributors: [Please provide the contributors]

Citations and References: [Please provide any citations or references]

Contact Information: [Please provide contact information]

Repository URL: [Please provide the repository URL, if any]

Additional Comments or Notes: [Please provide any additional comments or notes]

---