From a6e9f474768a6470ecb6fbefed4e54b879706dd0 Mon Sep 17 00:00:00 2001 From: mudler <2420543+mudler@users.noreply.github.com> Date: Thu, 30 Jul 2026 09:53:18 +0000 Subject: [PATCH] chore: bump inference defaults from unsloth --- core/config/inference_defaults.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/core/config/inference_defaults.json b/core/config/inference_defaults.json index ca80a2b4c..158f6bc33 100644 --- a/core/config/inference_defaults.json +++ b/core/config/inference_defaults.json @@ -41,12 +41,12 @@ "glm-5": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":-1,"top_p":0.95}, "glm-4": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":-1,"top_p":0.95}, "nemotron": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":-1,"top_p":1}, - "minimax-m3": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":40,"top_p":0.95}, "minimax-m2.7": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":40,"top_p":0.95}, "minimax-m2.5": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":40,"top_p":0.95}, "minimax": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":40,"top_p":0.95}, "gpt-oss": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":0,"top_p":1}, "granite-4": {"min_p":0.01,"repeat_penalty":1,"temperature":0,"top_k":0,"top_p":1}, + "kimi-k3": {"min_p":0,"repeat_penalty":1,"temperature":1,"top_k":-1,"top_p":0.95}, "kimi-k2": {"min_p":0.01,"repeat_penalty":1,"temperature":0.6,"top_k":-1,"top_p":0.95}, "kimi": {"min_p":0.01,"repeat_penalty":1,"temperature":0.6,"top_k":-1,"top_p":0.95}, "lfm2": {"min_p":0.15,"repeat_penalty":1.05,"temperature":0.1,"top_k":50,"top_p":0.1}, @@ -58,5 +58,5 @@ "grok": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":-1,"top_p":0.95}, "mimo": {"min_p":0.01,"repeat_penalty":1,"temperature":0.7,"top_k":-1,"top_p":0.95} }, - "patterns": ["qwen3.6","qwen3.5","qwen3-coder","qwen3-next","qwen3-vl","qwen3","qwen2.5-coder","qwen2.5-vl","qwen2.5-omni","qwen2.5-math","qwen2.5","qwen2-vl","qwen2","qwq","gemma-4","gemma-3n","gemma-3","medgemma","gemma-2","llama-4","llama-3.3","llama-3.2","llama-3.1","llama-3","phi-4","phi-3","mistral-nemo","mistral-small","mistral-large","magistral","ministral","devstral","pixtral","deepseek-v4","deepseek-r1","deepseek-v3","deepseek-ocr","glm-5","glm-4","nemotron","minimax-m3","minimax-m2.7","minimax-m2.5","minimax","gpt-oss","granite-4","kimi-k2","kimi","lfm2","smollm","olmo","falcon","ernie","seed","grok","mimo"] + "patterns": ["qwen3.6","qwen3.5","qwen3-coder","qwen3-next","qwen3-vl","qwen3","qwen2.5-coder","qwen2.5-vl","qwen2.5-omni","qwen2.5-math","qwen2.5","qwen2-vl","qwen2","qwq","gemma-4","gemma-3n","gemma-3","medgemma","gemma-2","llama-4","llama-3.3","llama-3.2","llama-3.1","llama-3","phi-4","phi-3","mistral-nemo","mistral-small","mistral-large","magistral","ministral","devstral","pixtral","deepseek-v4","deepseek-r1","deepseek-v3","deepseek-ocr","glm-5","glm-4","nemotron","minimax-m2.7","minimax-m2.5","minimax","gpt-oss","granite-4","kimi-k3","kimi-k2","kimi","lfm2","smollm","olmo","falcon","ernie","seed","grok","mimo"] }