robber@lemmy.ml to LocalLLaMA@sh.itjust.worksEnglish · 1 month agoQwen3-Coder-Nexthuggingface.coexternal-linkmessage-square10fedilinkarrow-up125arrow-down10file-text
arrow-up125arrow-down1external-linkQwen3-Coder-Nexthuggingface.corobber@lemmy.ml to LocalLLaMA@sh.itjust.worksEnglish · 1 month agomessage-square10fedilinkfile-text
minus-squarezaidka@lemmy.calinkfedilinkEnglisharrow-up3·1 month agoLooks like a solid model based on my limited testing. Though tool calls frequently fail with “JSON parse error” in longer sessions in OpenCode and llama.cpp. Hoping that will be addressed soon.
minus-squarerobber@lemmy.mlOPlinkfedilinkEnglisharrow-up2·edit-21 month agoYeah I enjoy it as well. Just in case you missed it - a fix was merged into llama.cpp two days ago which is said to improve quality. Edit: I stand corrected - the fix for the issue you’re experiencing has not yet been merged.
Looks like a solid model based on my limited testing. Though tool calls frequently fail with “JSON parse error” in longer sessions in OpenCode and llama.cpp. Hoping that will be addressed soon.
Yeah I enjoy it as well. Just in case you missed it - a fix was merged into llama.cpp two days ago which is said to improve quality.
Edit: I stand corrected - the fix for the issue you’re experiencing has not yet been merged.