OpenRLHF/Llama-3-8b-rlhf-100k
OpenRLHF's Llama-3-8b-rlhf-100k is an 8 billion parameter Llama 3 model fine-tuned using Reinforcement Learning from Human Feedback (RLHF) for 100,000 samples. This model builds upon a Llama-3-8b-sft base and a Llama-3-8b-rm reward model, demonstrating improved conversational performance over its SFT base. It is optimized for generating more aligned and helpful responses in chat-based applications.
Hugging Face Popular Sampler Settings
Most commonly used values from Featherless users
temperature
This setting influences the sampling randomness. Lower values make the model more deterministic; higher values introduce randomness. Zero is greedy sampling.
top_p
This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.
top_k
This limits the number of top tokens to consider. Set to -1 to consider all tokens.
frequency_penalty
This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.
presence_penalty
This setting penalizes new tokens based on their presence in the generated text so far. Values > 0 encourage new tokens; < 0 encourages repetition.
repetition_penalty
This setting penalizes new tokens based on their appearance in the prompt and generated text. Values > 1 encourage new tokens; < 1 encourages repetition.
min_p
This setting representing the minimum probability for a token to be considered relative to the most likely token. Must be in [0, 1]. Set to 0 to disable.