Hugging Face's logo
Metal's picture
17 11

Metal

MetaIX
Wager's profile picture ningpengtao's profile picture thewise's profile picture
·

AI & ML interests

None yet

Organizations

None yet

MetaIX's activity

New activity in Aeala/Enterredaas-65b over 1 year ago

Pweh-pweh

3
#1 opened over 1 year ago by
MetaIX
New activity in Aeala/GPT4-x-AlpacaDente-30b over 1 year ago

Psst, You are divine

2
#1 opened almost 2 years ago by
MetaIX
New activity in MetaIX/GPT4-X-Alpaca-30B-4bit over 1 year ago

llama.cpp breaks quantized ggml file format

4
#11 opened almost 2 years ago by
Waldschrat
New activity in MetaIX/GPT4-X-Alpasta-30b almost 2 years ago

Prompt Format?

1
#4 opened almost 2 years ago by
gsaivinay
New activity in MetaIX/GPT4-X-Alpasta-30b-4bit almost 2 years ago

Please reconvert to new GGML format

4
#6 opened almost 2 years ago by
Delta36652
New activity in MetaIX/GPT4-X-Alpaca-30B-4bit almost 2 years ago

Best model I tested, but seems to have an issue on some tokens

2
#12 opened almost 2 years ago by
kbrkbr

What model_type to set between "None" and "llama"? And what prompt style to use? There are plenty of the latter in Ooba's TextGenWebUI as of now and I'm pretty much lost (see pics for clarification)

4
#10 opened almost 2 years ago by
sneedingface
New activity in MetaIX/GPT4-X-Alpasta-30b-4bit almost 2 years ago

Any chance of a 4_2 or 4_0 ggml quantization?

4
#4 opened almost 2 years ago by
spanielrassler

Upload gpt4-x-alpasta-4bit.safetensors
#5 opened almost 2 years ago by
MetaIX
New activity in MetaIX/GPT4-X-Alpasta-30b almost 2 years ago

Performance worse than plan alpaca lora 30b?

2
#2 opened almost 2 years ago by
Davidliudev

What is this?

6
#1 opened almost 2 years ago by
vdruts
New activity in MetaIX/GPT4-X-Alpasta-30b-4bit almost 2 years ago

Upload 8 files
#1 opened almost 2 years ago by
MetaIX
New activity in MetaIX/GPT4-X-Alpaca-30B-4bit almost 2 years ago

Model size for int4 fine tuning on rtx 3090

3
#2 opened almost 2 years ago by
KnutJaegersberg

Loaded the model but it wont respond and is stuck saying "typing" meanwhile gpu usage at 100%

1
#6 opened almost 2 years ago by
barncroft

Please, help :<

17
#7 opened almost 2 years ago by
ANGIPO

Error: Internal: src/sentencepiece_processor.cc in Ooba and KAI 4bit

4
#8 opened almost 2 years ago by
Co0ode
New activity in MetaIX/Alpaca-30B-Int4 almost 2 years ago

LORA model or standard finetune?

2
#1 opened almost 2 years ago by
ghogan42