juncongmoo/pyllama

Issues

• aria2c 'magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA' not working

  #87 opened 2 years ago by Nolyzlel
  2

• Question regarding EnergonAI repo

  #114 opened 10 months ago by philipp-fischer
  0

• Run 'inference.py' and 'model parallel group is not initialized'

  #86 opened 2 years ago by ildartregulov
  7

• torch.distributed.elastic.multiprocessing.errors.ChildFailedError

  #113 opened a year ago by sido420
  1

• 12GB card

  #109 opened a year ago by arthurwolf
  2

• Quick Question

  #112 opened a year ago by ArgusK17
  0

• Download 7B model seems stuck

  #104 opened 2 years ago by guanlinz
  9

• about rotary embedding in llama

  #83 opened a year ago by irasin
  2

• How to run an interactive mode in Jupyter?

  #111 opened a year ago by myrainbowandsky
  0

• Quantize Original LLaMA Model Files

  #60 opened 2 years ago by htcml
  3

• no module named llama

  #108 opened a year ago by Cooper-Ji
  1

• evaluating has an extremely large value when quantize to 4bit.

  #105 opened 2 years ago by JiachuanDENG
  1

• ModuleNotFoundError: No module named 'transformers'

  #67 opened 2 years ago by tasteitslight
  6

• NVMLError_NoPermission: Insufficient Permissions

  #106 opened 2 years ago by sz2three
  0

• Download watchdog kicking in? (M1 mac)

  #103 opened 2 years ago by kryt
  0

• Cannot run on Mac with Python 3.11.3

  #81 opened 2 years ago by kornhill
  6

• Downloading get stuck in infinite loop

  #56 opened 2 years ago by jarimustonen
  13

• RuntimeError: Error(s) in loading state_dict for LLaMAForCausalLM: Unexpected key(s) in state_dict:

  #102 opened 2 years ago by ZealHua
  0

• RecursionError running llama.download

  #90 opened 2 years ago by anyangpeng
  4

• Why are params.json empty?

  #93 opened 2 years ago by ItsCRC
  5

• Strange characters

  #82 opened 2 years ago by webpolis
  1

• RecursionError: maximum recursion depth exceeded while calling a Python object

  #101 opened 2 years ago by Vaibhav11002
  0

• shape mismatch error

  #100 opened 2 years ago by Celppu
  0

• an operation was attempted on something that is not a socket

  #99 opened 2 years ago by GameDevKitY
  0

• parameter inncorrect when I run make command

  #98 opened 2 years ago by GameDevKitY
  0

• gptq github

  #97 opened 2 years ago by austinmw
  4

• Try Modular - Mojo

  #96 opened 2 years ago by eznix86
  0

• Randomly get shape mismatch error

  #95 opened 2 years ago by vedantroy
  0

• Does this include the GPTQ quantization tricks?

  #94 opened 2 years ago by vedantroy
  0

• Quantize issue

  #92 opened 2 years ago by ZenekZombie
  0

• Is that possible to quantize a locally converted model, instead of downloading from hugging face?

  #91 opened 2 years ago by chigkim
  1

• downloading file to pyllama_data/30B/consolidated.00.pth ...please wait for a few minutes ...

  #88 opened 2 years ago by Nolyzlel
  2

• Apply Delta failed

  #85 opened 2 years ago by majidbhatti
  1

• already quantize to 4bit and get the model pyllama-7B4b.pt，but can not run in RTX3080. report torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 0; 10.00 GiB total capacity; 9.24 GiB already allocated;

  #57 opened 2 years ago by elven2016
  2

• Can't see progress bar

  #66 opened 2 years ago by rahulvigneswaran
  1

• How to run 13B model in a single GPU just by inference.by?

  #84 opened 2 years ago by statyui
  0

• Quantization with "groupsize" makes the results completely wrong.

  #58 opened 2 years ago by daniel-kukiela
  8

• Any way to infer a quantized model on multi GPUs?

  #61 opened 2 years ago by Imagium719
  1

• Killed

  #62 opened 2 years ago by javierp183
  6

• a questuon about the single GPU Inference

  #74 opened 2 years ago by TitleZ99
  1

• Inference Error :UnicodeDecodeError: 'utf-8' codec can't decode byte 0xe7 in position 18: invalid continuation byte"

  #80 opened 2 years ago by MaiziXiao
  0

• quantify llama 7B, the md5 value and the model size does not equals to the value in README

  #73 opened 2 years ago by balcklive
  6

• Readme Should Have Inference Command to use for Quantization in Text

  #72 opened 2 years ago by chigkim
  1

• Quantized version link suspect

  #78 opened 2 years ago by thistleknot
  1

• Can't Load Quantized Model with GPTQ-for-LLaMa

  #75 opened 2 years ago by chigkim
  2

• Is there a way to skip evaluating after quantizing because it takes forever?

  #77 opened 2 years ago by chigkim
  0

• Document if it works with CPU / Macos

  #69 opened 2 years ago by ikamensh
  0

• Has black formatting been considered?

  #65 opened 2 years ago by tanitna
  0

• How to run the gradio with 30B model? and what devices are needed? please

  #64 opened 2 years ago by TobiasWYH
  0

• Error trying Quantize 7B model to 8-bit

  #55 opened 2 years ago by guoti777
  2