Hugging Face's logo

TheBloke
/
stable-vicuna-13B-GPTQ

Text Generation Transformers Safetensors
English llama causal-lm text-generation-inference 4-bit precision
Model card Files Community
29
New discussion

Error running the code:

1
#29 opened 9 months ago by Andyrasika

How to run qlora with stable vicuna?

1
#28 opened 9 months ago by Andyrasika

Could not find model in TheBloke/stable-vicuna-13B-GPTQ

3
#27 opened 10 months ago by AB00k

HF/bitsandbytes load_in_4bit is now apparently live apparently! (in peft)

3
#24 opened 11 months ago by 2themaxx

Issue starting the webui

7
#23 opened 11 months ago by Depsi

Updated special_tokens_map.json

1
#22 opened 11 months ago by brandonglockaby

What are the hardware requirements for this? I am running out of memory on my RTX3060 Ti :o

2
#21 opened 12 months ago by yramshev

AttributeError: 'Offload_LlamaModel' object has no attribute 'preload'

13
#17 opened 12 months ago by yramshev

Attentions are all None

2
#16 opened 12 months ago by joshlevy89

OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory models\TheBlokestable-vicuna-13B-GPTQ.

13
#14 opened 12 months ago by Squeezitgirdle

some errors occured when I use the webui who can tell me why?

4
#13 opened 12 months ago by yogurt111

ask

3
#12 opened 12 months ago by ReD2401

using with transformers

2
#11 opened 12 months ago by thefaheem

Model's VRAM Utilisation

3
#10 opened 12 months ago by thefaheem

Unable to load it using --pre_layer flag

5
#5 opened 12 months ago by boricuapab

the model thinks its chatgpt, lobotomy is advised

2
#4 opened 12 months ago by eucdee

No such file or directory: ‘models\TheBloke_stable-vicuna-13B-GPTQ\pytorch_model-00001-of-00003.bin’

9
#2 opened 12 months ago by Blue-Devil

stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors not compatible with "standard" settings

25
#1 opened 12 months ago by vmajor