CharlesLi/llama_2_rlhf_safe_llama_3_8B_default_1000_full

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

The CharlesLi/llama_2_rlhf_safe_llama_3_8B_default_1000_full model is a 7 billion parameter language model, fine-tuned from Meta's Llama-2-7b-chat-hf. This model is specifically fine-tuned on a generator dataset, achieving a loss of 0.9608 on its evaluation set. It is designed for generative tasks, leveraging the Llama 2 architecture for conversational applications.

Loading preview...

Model Overview

This model, llama_2_rlhf_safe_llama_3_8B_default_1000_full, is a fine-tuned variant of Meta's Llama-2-7b-chat-hf.

Key Characteristics

  • Base Model: Fine-tuned from meta-llama/Llama-2-7b-chat-hf.
  • Parameter Count: 7 billion parameters.
  • Fine-tuning Focus: Optimized on a specific "generator dataset" to enhance its generative capabilities.
  • Performance: Achieved a loss of 0.9608 on its evaluation set during training.

Training Details

The model was trained with the following hyperparameters:

  • Learning Rate: 2e-05
  • Batch Size: train_batch_size of 4, eval_batch_size of 4, leading to a total_train_batch_size of 32 and total_eval_batch_size of 16.
  • Optimizer: Adam with default betas and epsilon.
  • Scheduler: Cosine learning rate scheduler with a warmup ratio of 0.1.
  • Epochs: Trained for 1 epoch.

Intended Use Cases

Given its fine-tuning on a generator dataset, this model is suitable for tasks requiring text generation, conversational AI, and other applications where a robust generative language model is beneficial. Users should be aware that specific intended uses and limitations are not extensively detailed in the provided documentation.

Finetunes
1 models