From 62db1a70aac2864d7189f0007b00342db67283e8 Mon Sep 17 00:00:00 2001 From: ViperEkura <3081035982@qq.com> Date: Sun, 14 Jun 2026 19:08:43 +0800 Subject: [PATCH] switch to Qwen2.5-7B-Instruct --- opencode.json | 9 ++++----- server.py | 8 ++++---- 2 files changed, 8 insertions(+), 9 deletions(-) diff --git a/opencode.json b/opencode.json index 9b76881..9f04ff5 100644 --- a/opencode.json +++ b/opencode.json @@ -8,12 +8,11 @@ "apiKey": "not-needed" }, "models": { - "GLM-4.6V-Flash": { - "id": "GLM-4.6V-Flash", - "name": "GLM-4.6V-Flash", + "Qwen2.5-7B-Instruct": { + "id": "Qwen2.5-7B-Instruct", + "name": "Qwen2.5-7B-Instruct", "limit": { "context": 32768, "output": 8192 }, - "cost": { "input": 0, "output": 0 }, - "modalities": { "input": ["text", "image"], "output": ["text"] } + "cost": { "input": 0, "output": 0 } } } } diff --git a/server.py b/server.py index baa5de3..77da059 100644 --- a/server.py +++ b/server.py @@ -20,7 +20,7 @@ def _pick_free_gpu(): if __name__ == "__main__": _pick_free_gpu() - model = str(Path(__file__).resolve().parent / "models/GLM-4.6V-Flash") + model = str(Path(__file__).resolve().parent / "models/Qwen2.5-7B-Instruct") os.environ["FLASHINFER_DISABLE_VERSION_CHECK"] = "1" @@ -29,14 +29,14 @@ if __name__ == "__main__": model, "--host", "0.0.0.0", "--port", "8000", - "--served-model-name", "GLM-4.6V-Flash", + "--served-model-name", "Qwen2.5-7B-Instruct", "--trust-remote-code", - "--enable-auto-tool-choice", - "--tool-call-parser", "glm47", "--max-model-len", "32768", "--dtype", "bfloat16", "--gpu-memory-utilization", "0.85", "--enforce-eager", + "--enable-auto-tool-choice", + "--tool-call-parser", "openai", "--generation-config", "vllm", "--override-generation-config", '{"temperature": 0.8, "top_k": 50, "top_p": 0.9}', ])