mergekit-community/nsfw-w-deepseek-r1-retry
The mergekit-community/nsfw-w-deepseek-r1-retry model is a merged language model created using the Model Stock method, based on mergekit-community/nsfw_merge_test_vFFS. It combines stepenZEN/DeepSeek-R1-Distill-Llama-8B-Abliterated with various Llama-3 LoRAs, including Azazelle/Llama-3-LongStory-LORA, moetezsa/Llama3_instruct_on_wikibio, and Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B. This 8B parameter model is designed to integrate diverse capabilities from its constituent models, likely focusing on instruction following and narrative generation, given the Llama-3 LoRA components.
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.