CharlesLi/llama_2_rlhf_safe_llama_3_70B_default_100_full
The CharlesLi/llama_2_rlhf_safe_llama_3_70B_default_100_full model is a 7 billion parameter language model, fine-tuned from meta-llama/Llama-2-7b-chat-hf. This model has undergone specific fine-tuning on a generator dataset, achieving a loss of 1.6289 on its evaluation set. It is intended for applications requiring a Llama-2-based model with this particular fine-tuning profile.
Loading preview...
Model Overview
This model, llama_2_rlhf_safe_llama_3_70B_default_100_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 focus on a specific "generator dataset." The training process utilized a learning rate of 2e-05, a total batch size of 32, and ran for 1 epoch, achieving a reported loss of 1.6289 on its evaluation set.
Key Training Details
- Base Model: meta-llama/Llama-2-7b-chat-hf
- Parameters: 7 Billion
- Training Objective: Fine-tuned on a generator dataset.
- Evaluation Metric: Achieved a loss of 1.6289.
- Hyperparameters: Learning rate of 2e-05, Adam optimizer, cosine LR scheduler with 0.1 warmup ratio.
- Frameworks: Transformers 4.44.2, Pytorch 2.4.1+cu121, Datasets 3.0.0, Tokenizers 0.19.1.
Intended Use Cases
This model is suitable for developers looking to leverage a Llama-2-7b-chat-hf derivative that has undergone specific fine-tuning on a generator dataset. Its performance metrics suggest it is optimized for tasks aligned with its training data, though specific applications and limitations require further information not detailed in the provided README.