agentica-org/DeepScaleR-1.5B-Preview
DeepScaleR-1.5B-Preview is a 1.5 billion parameter language model developed by agentica-org, fine-tuned from DeepSeek-R1-Distilled-Qwen-1.5B using distributed reinforcement learning. It is specifically optimized for mathematical reasoning and problem-solving, achieving 43.1% Pass@1 accuracy on AIME 2024. This model demonstrates strong performance in mathematical benchmarks, surpassing larger models like OpenAI's O1-Preview with a significantly smaller parameter count.
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.
ā
frequency_penalty
This setting penalizes new tokens based on their frequency in the generated text. Values > 0 encourage new tokens; < 0 encourages repetition.
ā
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.
ā
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.
ā