Home
Register
Login
Login
Ph0rk0z
Threads posted
Replies posted
Ph0rk0z
2023-02-01
Can pascal ever be supported? Is it a lost cause?
0
Likes
1
Replies
Ph0rk0z
2023-03-05
Multiprocess, Multithreading and Paralelism
0
Likes
2
Replies
Ph0rk0z
2023-03-06
Question: When accelerate is used for offloading to CPU/CPUram only one core of the CPU is utilized.
0
Likes
3
Replies
Ph0rk0z
2023-03-15
Saving your name at least?
0
Likes
2
Replies
Ph0rk0z
2023-03-15
Switching to another model in the UI from GPTQ causes it to load in GPTQ.
0
Likes
0
Replies
Ph0rk0z
2023-03-18
There're no nodes connected, can't save settings.
0
Likes
0
Replies
Ph0rk0z
2023-03-18
Llama HF weights are supposed to be deterministic?
0
Likes
1
Replies
Ph0rk0z
2023-03-19
Visible Token counts for context/prompt/character
1
Likes
0
Replies
Ph0rk0z
2023-03-23
Other stopping conditions besides new line
4
Likes
4
Replies
AlexysLovesLexxie
2023-03-15
Recent changes causing short low-token responses with little to no RP Text.
0
Likes
19
Replies
HisashiASM
2023-03-19
Killed while loading pygmalion-6b_dev, GPT-J and other recent models
0
Likes
11
Replies
HisashiASM
2023-03-19
Killed while loading pygmalion-6b_dev, GPT-J and other recent models
0
Likes
11
Replies
Dampfinchen
2023-03-19
Improve memory management
0
Likes
17
Replies
Ph0rk0z
2023-03-05
Multiprocess, Multithreading and Paralelism
0
Likes
2
Replies
uckthis
2023-03-05
This app can't run on your PC
0
Likes
8
Replies
uckthis
2023-03-05
This app can't run on your PC
0
Likes
8
Replies
uckthis
2023-03-05
This app can't run on your PC
0
Likes
8
Replies
perkel666
2023-03-04
LLAMA model. RuntimeError: The expanded size of the tensor (2048) must match the existing size (2095)
0
Likes
2
Replies
Ph0rk0z
2023-03-18
Llama HF weights are supposed to be deterministic?
0
Likes
1
Replies
abhishekkrthakur
2023-02-05
`cuda_setup` is not defined
0
Likes
9
Replies
abhishekkrthakur
2023-02-05
`cuda_setup` is not defined
0
Likes
9
Replies
AlexysLovesLexxie
2023-03-08
Chat log no longer dims when generating
0
Likes
3
Replies
pamparamm
2023-03-08
Inference speedup possibilities
3
Likes
4
Replies
dnhkng
2023-03-14
RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
0
Likes
4
Replies
pamparamm
2023-03-08
Inference speedup possibilities
3
Likes
4
Replies
lucasbr15
2023-03-10
Suggestion to add: --autolaunch
0
Likes
2
Replies
Ph0rk0z
2023-03-15
Saving your name at least?
0
Likes
2
Replies
AlexysLovesLexxie
2023-03-15
Recent changes causing short low-token responses with little to no RP Text.
0
Likes
19
Replies
win10ogod
2023-03-15
Hi, Can hard disk virtual memory be used?
0
Likes
1
Replies
AlexysLovesLexxie
2023-03-15
Recent changes causing short low-token responses with little to no RP Text.
0
Likes
19
Replies
dnhkng
2023-03-14
RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
0
Likes
4
Replies
KnutJaegersberg
2023-03-16
Link to llama 13b fine tuned with RLHF & SFT by Swype
0
Likes
5
Replies
AlexysLovesLexxie
2023-03-18
undefined symbol: cget_col_row_stats / 8-bit not working / libsbitsandbytes_cpu.so not found
0
Likes
23
Replies
AlexysLovesLexxie
2023-03-15
Recent changes causing short low-token responses with little to no RP Text.
0
Likes
19
Replies
wk-mike
2023-03-17
"cublasLt ran into an error" with older GPU in 8-bit mode
0
Likes
12
Replies
Nicoyamata
2023-03-18
Unable to install on windows 11 22H2 (OS Build 25290.1010)
0
Likes
6
Replies
kft334
2023-03-18
Add support for loading pre-quantized Open-Assistant 4-bit
0
Likes
1
Replies
AlexysLovesLexxie
2023-03-18
Bot not using its own name.
0
Likes
3
Replies
Nicoyamata
2023-03-18
Unable to install on windows 11 22H2 (OS Build 25290.1010)
0
Likes
6
Replies
Nicoyamata
2023-03-18
Unable to install on windows 11 22H2 (OS Build 25290.1010)
0
Likes
6
Replies
HCBlackFox
2023-03-19
How to set a number of cpu thereds to use?
0
Likes
1
Replies
wk-mike
2023-03-17
"cublasLt ran into an error" with older GPU in 8-bit mode
0
Likes
12
Replies
Dampfinchen
2023-03-19
Improve memory management
0
Likes
17
Replies
HisashiASM
2023-03-19
Killed while loading pygmalion-6b_dev, GPT-J and other recent models
0
Likes
11
Replies
alexl83
2023-03-19
server.py not starting with GPTQ latest git 534edc7
0
Likes
34
Replies
Dampfinchen
2023-03-19
Improve memory management
0
Likes
17
Replies
TalhaErenY
2023-03-18
CUDA error when loading LLaMa model in Ubuntu WSL
0
Likes
9
Replies
Ph0rk0z
2023-03-06
Question: When accelerate is used for offloading to CPU/CPUram only one core of the CPU is utilized.
0
Likes
3
Replies
trimechee
2022-08-07
Failure to disable cach disk with command line which causes ruin because of Heavy I/O that destroys SSD because of the cache !
0
Likes
13
Replies
trimechee
2022-08-07
Failure to disable cach disk with command line which causes ruin because of Heavy I/O that destroys SSD because of the cache !
0
Likes
13
Replies
trimechee
2022-08-07
Failure to disable cach disk with command line which causes ruin because of Heavy I/O that destroys SSD because of the cache !
0
Likes
13
Replies
inferenceus
2022-09-19
Possible Licensing Violation
0
Likes
7
Replies
0cc4m
2023-02-25
NaN error when using a GPU with no support for igemmlt
0
Likes
4
Replies
tareaps
2023-03-23
error when starting the 4bit model
0
Likes
4
Replies
0cc4m
2023-02-25
NaN error when using a GPU with no support for igemmlt
0
Likes
4
Replies
DaBajan
2023-03-23
"RuntimeError: probability tensor contains either `inf`, `nan` or element < 0" 8bit mode not working 1070 Ti.
0
Likes
8
Replies
DaBajan
2023-03-23
"RuntimeError: probability tensor contains either `inf`, `nan` or element < 0" 8bit mode not working 1070 Ti.
0
Likes
8
Replies
DaBajan
2023-03-23
"RuntimeError: probability tensor contains either `inf`, `nan` or element < 0" 8bit mode not working 1070 Ti.
0
Likes
8
Replies
Wingie
2023-03-20
Support Laions open assistant model
0
Likes
2
Replies
© 2022 pullanswer.com - All rights reserved.
Privacy policy
