fix: update vLLM model to AxionML/Qwen3.5-9B-NVFP4

This commit is contained in:
Celes Renata
2026-04-23 19:30:22 +00:00
parent 5cf60be76d
commit 4bee7a7874
2 changed files with 2 additions and 2 deletions
+1 -1
View File
@@ -43,7 +43,7 @@ config:
OLLAMA_BASE_URL: "http://192.168.42.254:11434" OLLAMA_BASE_URL: "http://192.168.42.254:11434"
OLLAMA_MODEL: "qwen3.6" OLLAMA_MODEL: "qwen3.6"
VLLM_BASE_URL: "http://192.168.42.254:8000" VLLM_BASE_URL: "http://192.168.42.254:8000"
VLLM_MODEL: "RedHatAI/Qwen3.6-35B-A3B-NVFP4" VLLM_MODEL: "AxionML/Qwen3.5-9B-NVFP4"
VLLM_TIMEOUT: "120" VLLM_TIMEOUT: "120"
VLLM_MAX_RETRIES: "2" VLLM_MAX_RETRIES: "2"
VLLM_TEMPERATURE: "0.7" VLLM_TEMPERATURE: "0.7"
+1 -1
View File
@@ -182,7 +182,7 @@ config:
OLLAMA_RETRY_MAX_DELAY: "10.0" OLLAMA_RETRY_MAX_DELAY: "10.0"
OLLAMA_RETRY_BACKOFF_MULTIPLIER: "2.0" OLLAMA_RETRY_BACKOFF_MULTIPLIER: "2.0"
VLLM_BASE_URL: "http://192.168.42.254:8000" VLLM_BASE_URL: "http://192.168.42.254:8000"
VLLM_MODEL: "RedHatAI/Qwen3.6-35B-A3B-NVFP4" VLLM_MODEL: "AxionML/Qwen3.5-9B-NVFP4"
VLLM_TIMEOUT: "120" VLLM_TIMEOUT: "120"
VLLM_MAX_RETRIES: "2" VLLM_MAX_RETRIES: "2"
VLLM_TEMPERATURE: "0.7" VLLM_TEMPERATURE: "0.7"