[Model] Support for Spark2_5ForCausalLM implementation by KnightYao · Pull Request #27868 · ggml-org/llama.cpp
XHToken 推出了 Spark-X2.5-4B 和 Spark-X2.5-1.7B 两款紧凑型通用语言模型，旨在提供更实用、高效且易于访问的 AI。这些模型在对话、写作、翻译、推理、编码、工具使用和智能体工作流等日常任务中表现出色，在同等规模的开源模型中取得了领先成果。Spark-X2.5 结合了注重效率的架构，支持高达 1M token 的原生上下文窗口，并支持 200 多种语言。它们在华为昇腾集群上进行训练，利用 MOPD 等先进训练算法显著增强了推理、编码、智能体和指令遵循能力。
- 发布
- 2026年9月6日 16:36
- 来源类型
- 开发者社区
- 档位
- 社区
- 信源状态
- 正常
时间以 UTC 显示
更多信息
We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose language models designed to make capable AI more practical, efficient, and accessible. The models deliver strong performance across a broad range of everyday tasks—including conversation, writing, translation, reasoning, coding, tool use, and agentic workflows—achieving leading results among open-source models of comparable size. Spark-X2.5 combines an efficiency-oriented architecture with native context windows of up to 1M tokens, and support for more than 200 languages.
- Efficient Architecture and Native 1M-token Context: The models use a hybrid attention architecture that combines one full-attention layer with three sliding-window attention layers. This design substantially reduces the computational overhead typically associated with long-context models while natively supporting a context window of up to 1M tokens.
- Strong Coding and Agent Capabilities: The models are deeply integrated with popular agent harnesses, including Codex, Claude Code, OpenClaw, and Hermes. They deliver state-of-the-art performance among models of comparable size across everyday coding, agentic workflows, reasoning, and instruction-following tasks.
- Broad Hardware and Software Compatibility: The models support a wide range of hardware platforms, including NVIDIA, Huawei, Hygon, HOUMO.AI , etc. It is compatible with leading inference frameworks such as vLLM, SGLang, llama.cpp, MLX, and can be deployed quickly through platforms including Ollama and LM Studio. The models can also be customized using popular fine-tuning frameworks such as LLaMA-Factory. Across multiple hardware platforms, they deliver superior TTFT, TOPT, and overall inference efficiency compared with similarly sized models.
- Advanced Training Algorithms: The models were trained on Huawei Ascend clusters. Large-scale reinforcement learning and post-training techniques such as MOPD significantly enhance its reasoning, coding, agentic, and instruction-following capabilities.