mmnga/Llama-3-70B-japanese-suzume-vector-v0.1
The mmnga/Llama-3-70B-japanese-suzume-vector-v0.1 is an experimental 70 billion parameter Llama-3-based model developed by mmnga, designed to integrate Japanese language capabilities into the Meta-Llama-3-70B-Instruct model. This model applies a chat-vector approach by extracting differences between a Japanese-tuned 8B model and the base Llama-3-8B-Instruct, then upsampling and applying these differences to the larger 70B model. Its primary purpose is to explore methods for transferring language-specific fine-tuning from smaller models to larger Llama-3 variants for enhanced Japanese language processing.
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.
–