cjvt/GaMS-27B-Instruct-Nemotron
cjvt/GaMS-27B-Instruct-Nemotron is an instruction-tuned variant of the GaMS-27B-Instruct model, developed by Timotej Petrič as part of a master thesis project. It was fine-tuned using a curated subset of the nvidia/Nemotron-Post-Training-Dataset-v1, specifically optimized for bilingual performance. The training data includes approximately 80,000 Slovenian and 20,000 English instruction-response pairs, making it particularly strong in Slovenian language tasks.
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.
–