Abstract: A system for providing code suggestions according to licensing criteria is described. The system comprises computing devices that implement a code suggestion service. The code suggestion service receives a request that specifies licensing criteria via an interface of the code suggestion service. The code suggestion service determines respective licenses for respective source code files according to a source code attribution database from parsing the plurality of source code files that are applicable to the plurality of source code files. The code suggestion service generates a set of candidate code suggestions based, at least in part, on the plurality of source code files. The code suggestion service determines code suggestions from the set of candidate code suggestions that satisfy the licensing criteria based on the respective licenses. The code suggestion service provides the code suggestions determined from the set of candidate source code files that satisfy the licensing criteria.

Abstract: Evaluation data sets may be programmatically generated for code generation models. An evaluation data set is obtained that includes items that correspond to different evaluation tests for a code generation system. The individual items of the evaluation data set maybe converted, including the conversion of a function signature for the items, the test statements for the items and using a code generation system to generate the body of the function.

Abstract: Pre-fix matching may constrain the generation of next token predictions. Input text to perform a next token prediction may be received. Multiple tokens may be determined from the input text, including a partial token. From possible tokens, one or more matching possible tokens with the partial token may be identified. Next token predictions may then be filtered using the identified possible tokens in order to ensure that the partial token is matched.

Abstract: Random token segmentation may be implemented for next token prediction. Text data may be received for training a machine learning model to predict a next token given input text tokens. Multiple tokens may be determined from the text data. Different ones of the multiple token may be randomly segmented in to sub-tokens. The machine learning model may then be trained using the multiple tokens including the respective sub-tokens as a training data set.

Abstract: A protective bracket and a using method thereof. The protective bracket including: a main body part; an extension part extending outwardly from the main body part, at least part of the extension part being inclined relative to the main body part; a fixing part, extending from a free end of the extension part away from the main body part; a stopping part, connected to the main body part at a preset angle, in a thickness direction of the main body part, the fixing part and the stopping part being located at a same side of the main body part, and an end face of the fixing part away from the main body part being closer to the main body part than an end face of the stopping part away from the main body part.

Abstract: Disclosed by embodiments of the present application are an optical adhesive tape and a display panel. The optical adhesive tape includes a first buffer layer and an opening disposed at a position corresponding to the fingerprint identification area and configured to penetrate the first buffer layer. The opening is filled with a removable filler including a second buffer layer.

Abstract: A display module includes a functional layer and a display panel. The display module is provided with a hole region, a display region and a non-display region between the hole region and the display region. A through hole is provided at a portion of the functional layer and the display panel corresponding to the hole region. The display module includes a light shielding layer and a non-display portion located in the non-display region. In a thickness direction of the display module, the sum of the thickness of the non-display portion and the thickness of the light shielding layer is the same as the sum of the thickness of the functional layer in the display region and the thickness of the display panel in the display region.