Menlo/Jan-nano-128k
Menlo/Jan-nano-128k is a 4 billion parameter compact language model developed by Alan Dao and Bach Vu Dinh, designed for research applications. This model features a native 128k context window, enabling efficient processing of extensive documents and complex multi-turn conversations without typical performance degradation. It excels at deep document analysis and multi-document synthesis, making it suitable for research requiring complex reasoning over large information sets. Jan-nano-128k maintains compatibility with Model Context Protocol (MCP) servers and shows improved performance with longer contexts compared to its predecessor.
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.
–