YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

this template works very well with calude code and ik_llama.cpp and i tested it

echo 0 | sudo tee /proc/sys/kernel/numa_balancing CUDA_VISIBLE_DEVICES=2,3,0,1
numactl --interleave=all
~/ik_llama.cpp/build/bin/llama-server
--model /mnt/nvme/Qwen3.8-Flash-Next-Q8_0-00001-of-00006.gguf
--chat-template-file /mnt/nvme/or.jinja
--chat-template-kwargs '{"reasoning_effort":"xhigh"}'
--tensor-split 2.5,4,0.6,0.2
-ot "blk.(47).ffn_.*_exps.=CUDA3"
-cmoe
--numa distribute
-c 160000
--batch-size 2500
--ubatch-size 2500
--cache-type-k q8_0
--cache-type-v q8_0
--temp 1.0
--top-p 0.95
--top-k 20
--min-p 0.0
--presence-penalty 0.0
--repeat-penalty 1.0
--parallel 1
--threads 42
--threads-batch 42
-ngl 100
--host 127.0.0.1
--port 8082
--jinja

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support