Autobots
autobots
AI & ML interests
Chatbots
Organizations
None yet
autobots's activity
Failure loading in text-generation-webui.
12
#1 opened 11 months ago
by
Nafnlaus
How to load the voice model?
1
#1 opened 11 months ago
by
cyberstrong
Repetition issues?
#1 opened 12 months ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
Is this the 'better than Lazarus' model?
6
#1 opened about 1 year ago
by
7erminalVelociraptor
Cocktail Testing and Discussion
156
#1 opened over 1 year ago
by
deleted
I get expected Float found Half error
3
#1 opened over 1 year ago
by
ElevenGames
RuntimeError: shape '[-1, 1024, 6656]' is invalid for input of size 44302336
15
#6 opened over 1 year ago
by
phooney
Initial testing (epoch 3)
46
#1 opened over 1 year ago
by
deleted
Beware! Requires new cuda.
13
#5 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
This is a v1 model. Doesn't run on newer GPTQ anymore.
#6 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
You may want to add an "act-order" GPTQ quantization.
5
#22 opened over 1 year ago
by
xzuyn
ggml-gpt-fourchannel-q4_0.bin does not work on llama.cpp
2
#1 opened over 1 year ago
by
FenixInDarkSolo
This config also has cache disabled.
1
#1 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
conig.json
1
#1 opened over 1 year ago
by
Raddix
Set "use_cache": true for a speedup.
1
#4 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
This is made with the larger lora?
4
#2 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
Loading the model 26gb?
2
#7 opened over 1 year ago
by
MooCow27
Can we get the GPTQ quantized model?
2
#5 opened over 1 year ago
by
TheYuriLover
Can you encode this without group size?
1
#3 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
What is v1/v2?
2
#1 opened over 1 year ago
by
clxy
Multimodal
#10 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)
Can't generate text.
#1 opened over 1 year ago
by
autobots
![](https://cdn-avatars.huggingface.co/v1/production/uploads/63f26d8a7ddf724fbcc274a0/hoCyIEo1UvOJnqaNOpVAh.jpeg)