diff --git a/stacks/litellm/conf/config.yaml b/stacks/litellm/conf/config.yaml index 517abf6..e602c8d 100644 --- a/stacks/litellm/conf/config.yaml +++ b/stacks/litellm/conf/config.yaml @@ -59,6 +59,7 @@ model_list: model: hosted_vllm/qwen3.5-122-a10b api_base: http://10.250.50.54:8013/v1 api_key: os.environ/VLLM_API_KEY + presence_penalty: 1.0 extra_body: chat_template_kwargs: enable_thinking: false @@ -96,6 +97,11 @@ model_list: # + --reasoning-parser qwen3. One upstream fanned out under qwen3.5-122-a10b[-reasoning] # + aliases qwen-large[-reasoning] + gen[-reasoning]; -reasoning variants enable # thinking. Keep api_base in sync. + # presence_penalty: 1.0 on ALL these qwen3.5-122-a10b records (+ summarizer-large + # above) — anti-repetition-loop damper for the abliterated/NVFP4 tendency (operator + # 2026-06-27). Gateway-tunable default (callers can override); bake the validated + # value into the vLLM serving def (stacks/qwen3.5-122b, --override-generation-config) + # once confirmed, to also cover direct (non-gateway) callers. # ⚠️ Worldtree CHARACTER backend (was bound to mistral-small-4) is dark until # repointed — operator-acknowledged. --- - model_name: qwen3.5-122-a10b @@ -103,6 +109,7 @@ model_list: model: hosted_vllm/qwen3.5-122-a10b api_base: http://10.250.50.54:8013/v1 api_key: os.environ/VLLM_API_KEY + presence_penalty: 1.0 extra_body: chat_template_kwargs: enable_thinking: false @@ -113,6 +120,7 @@ model_list: model: hosted_vllm/qwen3.5-122-a10b api_base: http://10.250.50.54:8013/v1 api_key: os.environ/VLLM_API_KEY + presence_penalty: 1.0 extra_body: chat_template_kwargs: enable_thinking: true @@ -123,6 +131,7 @@ model_list: model: hosted_vllm/qwen3.5-122-a10b api_base: http://10.250.50.54:8013/v1 api_key: os.environ/VLLM_API_KEY + presence_penalty: 1.0 extra_body: chat_template_kwargs: enable_thinking: false @@ -133,6 +142,7 @@ model_list: model: hosted_vllm/qwen3.5-122-a10b api_base: http://10.250.50.54:8013/v1 api_key: os.environ/VLLM_API_KEY + presence_penalty: 1.0 extra_body: chat_template_kwargs: enable_thinking: true @@ -143,6 +153,7 @@ model_list: model: hosted_vllm/qwen3.5-122-a10b api_base: http://10.250.50.54:8013/v1 api_key: os.environ/VLLM_API_KEY + presence_penalty: 1.0 extra_body: chat_template_kwargs: enable_thinking: false @@ -153,6 +164,7 @@ model_list: model: hosted_vllm/qwen3.5-122-a10b api_base: http://10.250.50.54:8013/v1 api_key: os.environ/VLLM_API_KEY + presence_penalty: 1.0 extra_body: chat_template_kwargs: enable_thinking: true