CharlesLi/llama_2_rlhf_safe_llama_3_70B_default_500_full

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jan 13, 2025License:llama2Architecture:Transformer Open Weights Cold

CharlesLi/llama_2_rlhf_safe_llama_3_70B_default_500_full is a 7 billion parameter language model, fine-tuned from Meta's Llama-2-7b-chat-hf. This model has undergone fine-tuning on a specific generator dataset, achieving a loss of 0.9015 on its evaluation set. It is intended for applications requiring a Llama-2-based model with specific fine-tuning characteristics.

Loading preview...

Model Overview

This model, llama_2_rlhf_safe_llama_3_70B_default_500_full, is a fine-tuned variant of the meta-llama/Llama-2-7b-chat-hf base model. It features 7 billion parameters and was trained with a context length of 4096 tokens. The fine-tuning process involved a specific generator dataset, resulting in an evaluation loss of 0.9015.

Training Details

The model was trained using the following key hyperparameters:

  • Learning Rate: 2e-05
  • Batch Sizes: train_batch_size of 4, eval_batch_size of 4
  • Optimizer: Adam with default betas and epsilon
  • Scheduler: Cosine learning rate scheduler with a 0.1 warmup ratio
  • Epochs: 1

Key Characteristics

  • Base Model: Fine-tuned from meta-llama/Llama-2-7b-chat-hf.
  • Parameter Count: 7 billion parameters.
  • Evaluation Performance: Achieved a loss of 0.9015 on its evaluation set, indicating its performance on the specific fine-tuning task.

Intended Use Cases

This model is suitable for applications that can leverage a Llama-2-7b-chat-hf derivative, particularly where its specific fine-tuning on a generator dataset aligns with the desired output characteristics. Developers should consider its base architecture and fine-tuning focus when integrating it into their projects.