SWE-Dev-32BZai org
Start Chat
32.8B Params FP8 Open Weights Inference Available

zai-org/SWE-Dev-32B is a 32.8 billion parameter language model developed by zai-org, specifically designed as an open-source agent for software engineering tasks. Based on the Qwen-2.5-Coder-32B-Instruct architecture, it excels at developer-oriented tasks like issue tracking, code localization, and test case generation. This model achieves a 36.6% solve rate on SWE-bench-Verified, demonstrating strong performance in automated software development.

Loading preview...

Parameters:32.8BContext length:32kArchitecture:TransformerPrecision:FP8Quantized variants:AvailableLast updated:April 2025
0.0M
0.0K

Model tree for

zai-org/SWE-Dev-32B
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.

–