Featherless
Magnum-v1-72b-Qwen2.5Gghfez
Start Chat
72.7B Params FP8 Inference Available

gghfez/Magnum-v1-72b-Qwen2.5 is a 72 billion parameter language model based on the Qwen2.5 architecture, created by merging the creative capabilities of anthracite-org/magnum-v1-72b with the updated Qwen/Qwen2.5-72B-Instruct. This model is designed to offer enhanced creativity while retaining the general improvements of Qwen2.5, including improved coding ability and awareness of recent world events. It is particularly suited for tasks requiring creative text generation and general instruction following.

Loading preview...

Quick Stats

1

Parameters:72.7BContext length:33kArchitecture:TransformerPrecision:FP8Quantized variants:AvailableLast updated:October 2024
0.0M
0.0K

Model tree for

gghfez/Magnum-v1-72b-Qwen2.5
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.

0.86

top_p

This setting controls the cumulative probability of considered top tokens. Must be in (0, 1]. Set to 1 to consider all tokens.

1

top_k

This limits the number of top tokens to consider. Set to -1 to consider all tokens.

60

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.

1

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.

0.08