wb
aae53d91b1
Adds repeat_penalty=1.15 and repeat_last_n=128 to suppress token repetition loops (e.g. "tragen" -> "tragen" -> ...). Also caps output via num_predict (default 4096, configurable via OLLAMA_NUM_PREDICT env var) as a hard stop in case the model still gets stuck. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
5 lines
136 B
Plaintext
5 lines
136 B
Plaintext
API_BASE=http://gx10.aquantico.lan:8093
|
|
OLLAMA_BASE_URL=http://gx10.aquantico.lan:11434
|
|
OLLAMA_MODEL=qwen3.5:9b
|
|
OLLAMA_NUM_PREDICT=4096
|