trying new models that use could possibly accept the HuggingFaceEndpoint API inference 6de20f5 teofizzy commited on 9 days ago
switched to qwen 32B - Instruct due to inference provider support 81d32dd teofizzy commited on 10 days ago
changed to use huggingface serverless endpoint with local CPU as a fallback f8266e7 teofizzy commited on 10 days ago
changed default ollama network port to match huggingface default bba20c4 teofizzy commited on 22 days ago