mirror/LocalAI
1
0 Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-10-28 09:08:54 -04:00
Code Issues Packages Projects Releases Wiki Activity

chore: bump inference defaults from unsloth (#12732)

Browse Source 
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
This commit is contained in:
github-actions[bot]andmudler authored and GitHub committed 2026-10-16 08:45:28 +02:00
1 parent 377e71b704
commit fdfb171c3e
1 file changed
+3 -1
Download Patch File Download Diff File Expand all files Collapse all files
core/config/inference_defaults.json
+3 -1
View File
@@ -23,6 +23,7 @@
"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-spark": {"min_p":0,"repeat_penalty":1,"temperature":1,"top_k":-1,"top_p":1},
"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},
@@ -44,6 +45,7 @@
"deepseek-ocr": {"min_p":0.01,"repeat_penalty":1,"temperature":0,"top_k":-1,"top_p":0.95},
"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-3.5": {"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-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},
@@ -62,5 +64,5 @@
"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": ["moss-tts-local-transformer-v1.5","moss-tts-nano","qwen3.8","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"]
"patterns": ["moss-tts-local-transformer-v1.5","moss-tts-nano","qwen3.8","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-spark","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-3.5","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"]
}