Joseph
Joseph717171
AI & ML interests
None yet
Recent Activity
liked
a model about 2 hours ago
unsloth/Qwen3.5-9B upvoted a collection about 3 hours ago
Qwen3.5 liked
a model 4 days ago
unsloth/Qwen3.5-35B-A3B Organizations
hallucinations
π 1
4
#15 opened 3 months ago
by
eXt73
FP8-Block > FP8-Dynamic - This Quant of Llama-3.1-8B-Instruct is π₯
#1 opened 3 months ago
by
Joseph717171
Works well converted to GGUF Q8_0
#1 opened 3 months ago
by
Joseph717171
HuggingFaceFW/finepdfs 3T tokens of non-GPT slop
β€οΈ 1
2
#2 opened 6 months ago
by
Joseph717171
Bartowski First to the Finish Line! ππ€π¦
π₯ 3
#1 opened 6 months ago
by
Joseph717171
Updated Dynamic DeepSeek-V3.1 GGUFs - even better performance than before! π
π π₯ 6
6
#9 opened 6 months ago
by
shimmyshimmer
MXFP4_MOE
π π₯ 1
11
#1 opened 7 months ago
by
marcelone
Always reply"Iβm sorry, but I canβt help with that."
7
#8 opened 7 months ago
by
dongshuyan
GGUF uploaded now + Chat template Fixes!
π€ π₯ 4
27
#2 opened 7 months ago
by
shimmyshimmer
Wow, amazing response time
π€ β 9
7
#1 opened 7 months ago
by
AlexPradas
Please add the imatrix that you guys used for Jan-Nano (it's missing)
#2 opened 8 months ago
by
Joseph717171
how did you do it?
2
#4 opened 9 months ago
by
ehartford
Do this to arcee-ai/homunculus
#4 opened 9 months ago
by
Joseph717171
Made a jinja template that works for lmstudio
π 1
1
#2 opened 9 months ago
by
debeast6
New activity in Joseph717171/Llama-3.1-SuperNova-Lite-8.0B-OQ8_0-F32.EF32.IQ4_K-Q8_0-GGUF 10 months ago
Good for summarization.
β€οΈ π₯ 1
6
#1 opened over 1 year ago
by
ThiloteE
Wrong model name in Model Card and Wrong Model Description
1
#2 opened 11 months ago
by
Joseph717171
Permission to access the Unquantized versions of the QAT weights for Gemma-3
π 2
10
#4 opened 11 months ago
by
Joseph717171
[MODELS] Discussion
β€οΈ π 38
800
#372 opened about 2 years ago
by
victor
Nice model, but it can sometimes be very insistently wrong.
10
#7 opened about 1 year ago
by
gpuftw
Good for coding?
π 1
3
#1 opened about 1 year ago
by
urtuuuu