huihui.ai PRO
huihui-ai
AI & ML interests
We are committed to the study of model ablations and collaborate with the open-source community to advance natural language
processing. You can follow https://x.com/support_huihui, then leave us a message.
Recent Activity
new activity about 8 hours ago
huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF:The newly added Huihui-Qwen3.8-27B-abliterated-GSQ-RCO is awesome updated a model about 19 hours ago
huihui-ai/Huihui-Spark-X2.5-4B-abliterated published a model about 19 hours ago
huihui-ai/Huihui-Spark-X2.5-4B-abliteratedOrganizations
The newly added Huihui-Qwen3.8-27B-abliterated-GSQ-RCO is awesome
🔥 1
3
#19 opened 3 days ago
by 
Abl1ttheworld
Request: true Q4_K routed-expert quant for Vision-Exp (non-MXFP4)
2
#3 opened 1 day ago
by 
krisanteaa
Deepseek v4.1 Flash
2
#1 opened 2 days ago
by 
ZHUOZA
Abliterated ISTA-DASLab Qwen3.8-27B-GSQ-RCO models
5
#18 opened 4 days ago
by 
mepstein
Question about safetensors/bf16 (layers 23–51 ablated) download
3
#17 opened 7 days ago
by 
fangkuaik
Praying for a UD-Q4_K_M
3
#15 opened 12 days ago
by 
nixudos
No MTP in UD-IQ2_S
2
#14 opened 12 days ago
by mepstein
Evidence of Residual Refusals
👍 1
2
#12 opened 15 days ago
by 
Kreflux
Kimi k3?
5
#10 opened 18 days ago
by 
singulariti
need gguf(+mtp）
1
#3 opened 19 days ago
by 
cleverhack
Request UD-IQ1_M ~
3
#9 opened 19 days ago
by 
sunnyboxs
Can we get UD quants? (UD-Q2_K_XL / UD-Q3_K_XL / UD-Q4_K_XL)
2
#8 opened 20 days ago
by 
denizaydemir
why Huihui-Qwen3.8-27B-abliterated-Q8_0_L.gguf is bigger than unsloth Q8-XL?
1
#7 opened 21 days ago
by 
akierum
Can we get Q6_K_XL
4
#5 opened 23 days ago
by 
snopchat
Why is there no model with IQ3 quantization?
2
#4 opened 24 days ago
by 
kent1065
发一个GUFF格式的
3
#1 opened 27 days ago
by 
kelei999999
Tests
🔥 2
4
#2 opened 27 days ago
by 
etemiz
MTP head weights corrupted by abliteration: --spec-type draft-mtp yields 0% acceptance
2
#4 opened 26 days ago
by 
wzgrx
unknown renderer "qwen3.8"
3
#2 opened 27 days ago
by 
intlex
