Skywork/Skywork-SWE-32B
Skywork-SWE-32B is a 32.8 billion parameter code agent model developed by Skywork AI, specifically designed for software engineering (SWE) tasks. Built on the Qwen2.5-Coder-32B-Instruct backbone, it achieves 38.0% pass@1 accuracy on the SWE-bench Verified benchmark, outperforming previous open-source models in its class. With a notable context length of 131072 tokens, this model excels at automated code generation and bug fixing within comprehensive executable runtime environments. Its performance can further improve to 47.0% accuracy with test-time scaling techniques, making it suitable for complex software development workflows.
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.
–