jpacifico/Chocolatine-3B-Instruct-DPO-Revised is a 3.82 billion parameter instruction-tuned causal language model developed by Jonathan Pacifico, fine-tuned from Microsoft's Phi-3-mini-4k-instruct. This model excels in French language tasks, outperforming GPT-3.5-Turbo on MT-Bench-French, and also shows improved performance in English compared to its base model. With a 4k token context window, it is currently the best-performing 3B model on the OpenLLM Leaderboard (August 2024), demonstrating strong general capabilities.
Loading preview...
Model tree for
jpacifico/Chocolatine-3B-Instruct-DPO-RevisedMost 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.