Featherless
QVikhr-2.5-1.5B-Instruct-SMPOVikhrmodels
Start Chat
1.5B Params BF16 Open Weights Inference Available

QVikhr-2.5-1.5B-Instruct-SMPO is a 1.5 billion parameter instruction-tuned causal language model developed by Vikhrmodels, based on Qwen-2.5-1.5B-Instruct. It is specialized for Russian language tasks while supporting bilingual RU/EN interactions, and has been aligned using Simple Margin Preference Optimization (SMPO) on the GrandMaster-PRO-MAX dataset to enhance response quality.

Loading preview...

Quick Stats

3

Parameters:1.5BContext length:33kArchitecture:TransformerPrecision:BF16Quantized variants:AvailableLast updated:January 2025
0.0M
0.0K

Model tree for

Vikhrmodels/QVikhr-2.5-1.5B-Instruct-SMPO
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.