From b89934cb46e4597b67f9d5724e9d3b0cf16e6106 Mon Sep 17 00:00:00 2001 From: jtwolfe <2417379+jtwolfe@users.noreply.github.com> Date: Sat, 4 Apr 2026 06:22:12 +0000 Subject: [PATCH] chore: bump inference defaults from unsloth --- core/config/inference_defaults.json | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/core/config/inference_defaults.json b/core/config/inference_defaults.json index 56109a040079..68548ff58ad7 100644 --- a/core/config/inference_defaults.json +++ b/core/config/inference_defaults.json @@ -14,6 +14,7 @@ "qwen2-vl": {"min_p":0.1,"repeat_penalty":1,"temperature":1.5,"top_k":-1,"top_p":0.95}, "qwen2": {"min_p":0,"repeat_penalty":1,"temperature":0.7,"top_k":20,"top_p":0.8}, "qwq": {"min_p":0,"repeat_penalty":1,"temperature":0.6,"top_k":40,"top_p":0.95}, + "gemma-4": {"min_p":0,"presence_penalty":0,"repeat_penalty":1,"temperature":1,"top_k":64,"top_p":0.95}, "gemma-3n": {"min_p":0,"repeat_penalty":1,"temperature":1,"top_k":64,"top_p":0.95}, "gemma-3": {"min_p":0,"repeat_penalty":1,"temperature":1,"top_k":64,"top_p":0.95}, "medgemma": {"min_p":0,"repeat_penalty":1,"temperature":1,"top_k":64,"top_p":0.95}, @@ -53,5 +54,5 @@ "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": ["qwen3.5","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-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-r1","deepseek-v3","deepseek-ocr","glm-5","glm-4","nemotron","minimax-m2.5","minimax","gpt-oss","granite-4","kimi-k2","kimi","lfm2","smollm","olmo","falcon","ernie","seed","grok","mimo"] + "patterns": ["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-r1","deepseek-v3","deepseek-ocr","glm-5","glm-4","nemotron","minimax-m2.5","minimax","gpt-oss","granite-4","kimi-k2","kimi","lfm2","smollm","olmo","falcon","ernie","seed","grok","mimo"] }