1M tokens of context. 4B parameters. Apache 2.0. Controllable thinking.
Spark-X2.6-4B is live, and vLLM serves it day 0. Congrats to the @SparkLLM team! 📷
vLLM serves Spark-X2.6-4B on day 0 with 1M-token context
AIvLLM says it serves Spark-X2.6-4B, a 4B-parameter model with 1M tokens of context, under Apache 2.0 with controllable thinking. The model is available on day 0 and is built by the SparkLLM team.
@vllm_project
Spark-X2.6-4B is here! Stronger coding, agents & long-context skills through improved post-training. Thinking: none / low / high. @huggingface @ModelScope2022 @ollama @vllm_project @sgl_project https://huggingface.co/XHToken/Spark-X2.6-4B
Source details
vLLM · x.comPublished · added here
Original title: 1M tokens of context. 4B parameters. Apache 2.0. Controllable thinking.