Ollama Modelfile to fix tool calling within GLM-4.7-Flash GGUF
pinned❤️ 3
3
#23 opened 21 days ago
by
CesarR70
DISABLE REPEAT PENALTY or set = 1.0
pinned👍 5
7
#13 opened about 1 month ago
by
danielhanchen
Jan 21: All GLM-4.7-Flash quants reuploaded - much better outputs!
pinned🔥 ❤️ 7
29
#10 opened about 1 month ago
by
danielhanchen
Model degrades after ~64000 tokens
#30 opened 9 days ago
by
ceoofcapybaras
Localai model load fails w/GLM-4.7-Flash-IQ4_XS.gguf
#29 opened 12 days ago
by
SplashMatic
New uploads Feb 12th?
👍 1
2
#27 opened 14 days ago
by
jmagder
Still looping and getting stuck thinking after new update
4
#26 opened 18 days ago
by
xantrk
Tool calls destroy good reasoning + how to fix it
#25 opened 19 days ago
by
ffewfqefwsefwfe
GLM-4.7-Flash-Q4_K_S - in LMStudio 4.0.2 = garbage
#24 opened 20 days ago
by
K-Tul-Khu
HumanEval Benchmarks: GLM-4.7-Flash (UD Q4/Q5)
#22 opened 25 days ago
by
k5uu5
NEW: LLama.cpp: Using `ngram-mod` to Get 2x Speed Boost on Long-Chats/Agent!
1
#20 opened 27 days ago
by
PussyHut
Getting 110 tokens/sec on my RTX 3090, 24 GB VRam
👍 🔥 4
#19 opened 29 days ago
by
bikkikumarsha
New flag: kv-unified. Performance report: 90 t/s on RTX 4090D 48GB
🔥 2
4
#18 opened about 1 month ago
by
SlavikF
Anyone tried to challenge the model?
3
#16 opened about 1 month ago
by
urtuuuu
Ollama Support
5
#15 opened about 1 month ago
by
yqchen-sci
Infinite thinking (after </thinking> tag with updated quants
5
#14 opened about 1 month ago
by
CoruNethron
new ggufs working as intended
🤗 🔥 1
1
#12 opened about 1 month ago
by
realrebelai
GGUF model with architecture deepseek2 is not supported yet.
2
#11 opened about 1 month ago
by
T1-Faker1
How to run properly on KoboldCPP?
2
#8 opened about 1 month ago
by
Varkoyote
Kind of broken.
14
#7 opened about 1 month ago
by
ItzPingCat
Disable thinking?
4
#4 opened about 1 month ago
by
JankyMudFart
Issue: GLM-4.7-Flash Q6_K - Completely unusable output (looping)
6
#3 opened about 1 month ago
by
gannima
Jan 21: GGUFs all UPDATED!!!
🤗 ❤️ 5
40
#1 opened about 1 month ago
by
danielhanchen