Search Results for "off-site.com"

FastVLM is an efficiency-focused vision-language modeling stack that introduces FastViTHD, a hybrid vision encoder engineered to emit fewer visual tokens and slash encoding time, especially for high-resolution images. Instead of elaborate pruning stages, the design trades off resolution and token count through input scaling, simplifying the pipeline while maintaining strong accuracy. Reported results highlight dramatic speedups in time-to-first-token and competitive quality versus contemporary open VLMs, including comparisons across small and larger variants. The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. ...

...This dataset covers project-level code structure (not just line-by-line snippets), using a large context window (e.g. 16K) and a secondary fill-in-the-blank objective to encourage better contextual completions and infilling. Multiple sizes of the model are offered (e.g. 1B, 5.7B, 6.7B, 33B) so users can trade off inference cost vs capability. The repo provides model weights, documentation on training setup, evaluation results on common benchmarks (HumanEval, MultiPL-E, APPS, etc.), and inference tools.

...Though smaller in scale, GLM-4.1V maintains competitive performance, particularly impressive on many benchmarks for models of its size: in fact, on a number of multimodal reasoning and vision-language tasks it outperforms some much larger models from other families. It represents a trade-off: somewhat reduced capacity compared to 4.5V or 4.6V, but with benefits in terms of speed, deployability, and lower hardware requirements — making it especially useful for developers experimenting locally, building lightweight agents, or deploying on limited infrastructure. Given its open-source availability under the same project repository, it provides an accessible entry point for testing multimodal reasoning and building proof-of-concept applications.

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called VALL-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. ...

...TimeSformer was influential in showing that pure transformer architectures—without convolutional backbones—can perform strongly on video classification tasks. Its flexible attention design allows experimenting with different factoring (spatial-then-temporal, joint, etc.) to trade off compute, memory, and accuracy.

...It supports up to 256K context tokens, advanced reasoning (CoT) abilities, and agent-based workflows with tool parsing. The model offers both fast and slow thinking modes, letting users trade off speed for deeper reasoning. It excels in mathematics, science, coding, and multi-turn conversation tasks, rivaling or outperforming larger models in several areas. Deployment is supported via TensorRT-LLM, vLLM, and SGLang, with Docker images and integration guides provided. Open-source under a custom license, it's ideal for researchers and developers seeking scalable, high-context AI capabilities with optimized inference.