marcel/phi-2-openhermes-30k
marcel/phi-2-openhermes-30k is a 3 billion parameter causal language model, converted to MLX format from Microsoft's Phi-2 base model and fine-tuned with the OpenHermes dataset. It features a 2048-token context length and demonstrates balanced performance across various reasoning and common sense benchmarks, including HellaSwag and Winogrande. This model is primarily suited for general-purpose text generation and conversational AI tasks, offering a compact yet capable solution for on-device or resource-constrained deployments.
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.
–