deep-diver/LLM-As-Chatbot

Issues

• gradio incompatibility

  #105 opened 8 months ago by mlinmg
  1

• Error on Mac M2 24GB RAM

  #90 opened a year ago by OmidH
  2

• Can't run starchat: fails with `AttributeError: module 'global_vars' has no attribute 'gen_config'`

  #75 opened a year ago by nathanielastudillo
  13

• Can't load tokenizer for 'elinas/llama-7b-hf-transformers-4.29'

  #94 opened a year ago by xiaoxingchen505
  2

• Can this be accessed via an OpenAI Compatible API

  #102 opened a year ago by mjtechguy
  0

• How to run on CPU?

  #101 opened a year ago by ratan
  0

• falcon 7b llm

  #100 opened a year ago by NavyashreeD13
  0

• Internet search is very slow using orca mini on 4bit in google colab T4 on gradio

  #98 opened a year ago by githubpradeep
  3

• PingPong cant be imported

  #95 opened a year ago by gavi
  1

• Error on Mac

  #93 opened a year ago by AndyBlocker
  1

• Data Customization

  #92 opened a year ago by Agbeli
  0

• Minor first run console errors.. Just passing along.

  #91 opened a year ago by linuxmagic-mp
  0

• LLM-As-Chatbot need GPU?

  #79 opened a year ago by mehrdad2000
  7

• Something went wrong Connection errored out. Loading checkpoint shards

  #86 opened a year ago by javierxio
  4

• ERROR: No matching distribution found for transformers[sentencepiece]<4.30.0,>=4.26.0

  #85 opened a year ago by javierxio
  1

• Can Ping Pong principle be applied to let 2 LLM Chatbots talk to each other fully automatically?

  #81 opened a year ago by jbdatascience
  4

• Should there be Docker instruction?

  #78 opened a year ago by Dref360
  1

• Dark Mode

  #71 opened a year ago by gavi
  2

• query regarding MPT, RedPajama and Falcon models

  #72 opened a year ago by GeorvityLabs
  17

• Default launch gets stuck at "Loading.."

  #70 opened a year ago by gavi
  2

• Traceback (most recent call last): File "F:\gpt\LLM-As-Chatbot-main\menu_app.py", line 7, in <module> import global_vars File "F:\gpt\LLM-As-Chatbot-main\global_vars.py", line 2, in <module> from transformers import GenerationConfig ImportError: cannot import name 'GenerationConfig' from 'transformers' (D:\Users\Administrator\anaconda3\lib\site-packages\transformers\__init__.py)

  #67 opened a year ago by 2662007798
  1

• cpu or amd gpu support

  #68 opened a year ago by gmankab
  2

• why do not support load from local dir but always download

  #66 opened a year ago by Xiang-cd
  1

• Use my model on local server

  #64 opened a year ago by tunglambk
  7

• Other LORA models

  #60 opened a year ago by philwee
  14

• Colab Notebook not working (and fix)

  #59 opened a year ago by philwee
  3

• Getting torch.cuda.OutOfMemoryError: CUDA out of memory

  #23 opened a year ago by imranraad07
  1

• add or not history_response

  #38 opened a year ago by lelegogo26
  1

• sharing any good conversation sequences

  #47 opened a year ago by deep-diver
  0

• prompt format (input vs instruction).

  #31 opened a year ago by wassname
  4

• [Backlog] Add sparse models to options

  #52 opened a year ago by claysauruswrecks
  2

• Issue with code - TensorRT not found

  #51 opened a year ago by DocML
  1

• Error with bitsandbytes and running at all.

  #37 opened a year ago by Websteria
  1

• How to run it with llama-7b-hf-int4?

  #25 opened a year ago by ZhUyU1997
  1

• Distillation

  #27 opened a year ago by maralski
  1

• i have some question about Input, Instruction, Response

  #54 opened a year ago by byeongcheoljo
  1

• AttributeError: module 'numpy' has no attribute 'object'

  #57 opened a year ago by csakaszamok
  1

• bug in chatbot UI

  #32 opened a year ago by GeorvityLabs
  27

• Is there any way to test the API with Postman and the Rest API?

  #56 opened a year ago by ShahrukhYousafzai
  0

• How can I test the API with Postman? as Rest API

  #55 opened a year ago by ShahrukhYousafzai
  0

• Something went wrong Expecting value: line 1 column 1 (char 0)

  #53 opened a year ago by cainiaoDJ
  3

• gradio running local: instant error, public: neverending wait time

  #42 opened a year ago by saveli
  5

• match model_type: error on latest commit

  #46 opened a year ago by cesarandreslopez
  5

• Any plan to support gptq?

  #39 opened a year ago by gaoxiao
  3

• future usage error

  #28 opened a year ago by suhwan-kang
  17

• Can this project run on apple silicon M1pro chip with 16G ram?

  #30 opened a year ago by bumblebeeK
  0

• Can the code use beam search in Streaming Mode?

  #29 opened a year ago by Facico
  2

• Run offline

  #26 opened a year ago by ManuXD32
  2

• Default models not working

  #21 opened a year ago by calz1
  1

• Is the "chansung/alpaca-lora-7b/" model private?

  #24 opened a year ago by mhmunem
  1