darkcloudai/huskylm-2.5-8b
The darkcloudai/huskylm-2.5-8b is an 8 billion parameter causal language model developed by Darkcloud AI, built upon Meta's Llama 3 architecture with an 8192 token context window. It is fine-tuned using a combination of Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and proprietary Reinforcement Learning from Artificial Intelligence Feedback (RLAIF) methodologies. This general-purpose chat model excels in strong system prompt adherence, state-of-the-art coding abilities across multiple languages, exceptional conversational skills, and best-in-class multilingual support, making it suitable for diverse applications from writing assistance to in-game NPC interactions.
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.