Files
instinct/README.md
ModelHub XC 30a711fc1d 初始化项目,由ModelHub XC社区提供模型
Model: continuedev/instinct
Source: Original Platform
2026-05-08 14:02:12 +08:00

1.5 KiB

license, datasets, base_model, pipeline_tag, library_name
license datasets base_model pipeline_tag library_name
apache-2.0
continuedev/instinct-data
Qwen/Qwen2.5-Coder-7B
text-generation transformers

Instinct, the State-of-the-Art Open Next Edit Model

This repo contains the model weights for Continue's state-of-the-art open Next Edit model, Instinct. Robustly fine-tuned from Qwen2.5-Coder-7B on our dataset of real-world code edits, Instinct intelligently predicts your next move to keep you in flow.

Serving the model

Ollama: We've released a Q4_K_M GGUF quantization of Instinct for efficient local inference. Try it with Continue's Ollama integration, or just run ollama run nate/instinct.

You can also serve the model using either of the below options, then connect it with Continue.

SGLang: python3 -m sglang.launch_server --model-path continuedev/instinct --load-format safetensors
vLLM: vllm serve continuedev/instinct --served-model-name instinct --load-format safetensors

Learn more

For more information on the work behind Instinct, please refer to our blog.