anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g

#55 opened about 1 year ago by

pasan-SK

Model cant be loaded

#54 opened over 1 year ago by

Tulakor

"RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!"

#53 opened almost 2 years ago by

sneet

Fine tuning "gpt4-x-alpaca-13b-native-4bit-128g".

#52 opened almost 2 years ago by

muzammil-eds

Setup on MBP

#51 opened almost 2 years ago by

NinjAIbot

IndexError: list index out of range

#50 opened almost 2 years ago by

zeyad-shaban

The model weights are not tied and json-files are different from the original LlamaTokenizer file?

#49 opened almost 2 years ago by deleted

error loading model: unexpectedly reached end of file

#48 opened almost 2 years ago by

toomox

Error: failed to load model 'ggml-model-q4_1.bin'

#47 opened almost 2 years ago by

Arthur-101

Any Constructive help is always welcome. :/

#46 opened almost 2 years ago by

TehNinja

Requantize to support latest code on llama.cpp

#45 opened almost 2 years ago by

TusharRay

你好

#44 opened almost 2 years ago by

SunYangGunang

Where is the info on how to format the prompt?

#43 opened almost 2 years ago by

MaxLohMusic

Out of memory? somehow

#42 opened about 2 years ago by

LudoPog

error, says this model is not found?

#41 opened about 2 years ago by

yutoliho

Running out of memory with 12GB of VRAM on 3080TI

#39 opened about 2 years ago by

faaaaaaaaaaaa

Issues running the model in python

#38 opened about 2 years ago by

Kralos-R

How I got this to run with oobabooga/ text-generation-webui

#37 opened about 2 years ago by

socter

Colab for finetuning

#36 opened about 2 years ago by

robertsw

RuntimeError: [enforce fail at C:\cb\pytorch_1000000000000\work\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 1048576 bytes.

#35 opened about 2 years ago by

FastRide2

gradio error?

#34 opened about 2 years ago by

JLEADO

Gpt4-x-alpaca gives gibberish numbers instead of words

#33 opened about 2 years ago by

Snim

RTX 3070, only getting about 0,38 tokens/minute

#32 opened about 2 years ago by

jojokingxp45

No response from Abaca when using GPU version

#31 opened about 2 years ago by

ZeroH3art

For those who complain about that its Censored

#30 opened about 2 years ago by

Shivero

Running an rtx3060 with 12GBvram - managed to get this model working on method in link in description

#28 opened about 2 years ago by

planetfrog

RuntimeError: Internal: D:\a\sentencepiece\sentencepiece\src\sentencepiece_processor.cc(1102) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

5

#27 opened about 2 years ago by deleted

for people with low Mid pc specs

#26 opened about 2 years ago by

bhaveshNOm

Request for Colab Version

5

#25 opened about 2 years ago by

zaeaz

Emoji overload

#24 opened about 2 years ago by

Horned

ValueError: Tokenizer class LlamaTokenizer does not exist or is not currently imported. (while using Transformers)

#23 opened about 2 years ago by

ShifraSec

Temporal fix for "DefaultCPUAIIocator: not enough memory: you tried to allocate 13107200 bytes" error

#22 opened about 2 years ago by

xiiredrum

Issue with tokenizor using Ooga Booga?

#21 opened about 2 years ago by

mm04926412

Stuck at "Filtering content: 40% (2/5)" when cloning repository

13

#20 opened about 2 years ago by

splork

I'm trying to run this using oobabooga but I'm getting 0.17 tokens/second.

5

#18 opened about 2 years ago by

Said2k

LLAMA running slow with this model.

#17 opened about 2 years ago by

BoreGuy1998

Error loading gpt4-x-alpaca-13b-native-4bit-128g on Alienware M15 Ryzen Edition R5 laptop

#16 opened about 2 years ago by

Omarrrrz

out of memory error when launching from oobabooga web ui

34

#15 opened about 2 years ago by

bhaveshNOm

torch.cuda.OutOfMemoryError

#14 opened about 2 years ago by

Forceee

Only small amount of tokens generated in oobabooga

#13 opened about 2 years ago by

synthetisoft

Is Vicuna involved by any means?

#12 opened about 2 years ago by

sneedingface

Does this model able to run on 3060 12g?

#11 opened about 2 years ago by

cyx123

CUDA out of memory

#10 opened about 2 years ago by

n01sf8

Cuda error with ooba-booga WebUI

#9 opened about 2 years ago by

Timo956

Hmmm.... Problem with another language...

#8 opened about 2 years ago by

RGTails

Safetensors version?

#7 opened about 2 years ago by

shalak

Error using ooba-gooba

39

#6 opened about 2 years ago by

blueisbest

7B model thanks?

#4 opened about 2 years ago by

tamal777

How can i use this model with GPTQ-for-LLaMa?

#3 opened about 2 years ago by

jini1114

Error for LlamaForCausalLM.from_pretrained in HuggingFace