chore: bump inference defaults from unsloth (#11270)

Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
This commit is contained in:
github-actions[bot]andmudler authored and GitHub committed 2026-08-12 09:12:12 +02:00
1 parent 3ec466b61b
commit b7a0646587
1 file changed
+3 -2
+3 -2
View File
@@ -20,6 +20,7 @@
"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},
"gemma-2": {"min_p":0,"repeat_penalty":1,"temperature":1,"top_k":64,"top_p":0.95},
"muse-glimmer": {"min_p":0,"repeat_penalty":1,"temperature":1,"top_k":64,"top_p":0.95},
"llama-4": {"min_p":0.01,"repeat_penalty":1,"temperature":1,"top_k":-1,"top_p":0.9},
"llama-3.3": {"min_p":0.1,"repeat_penalty":1,"temperature":1.5,"top_k":-1,"top_p":0.95},
"llama-3.2": {"min_p":0.1,"repeat_penalty":1,"temperature":1.5,"top_k":-1,"top_p":0.95},
@@ -41,12 +42,12 @@
"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 +59,5 @@
"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","muse-glimmer","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"]
}