liltom-eth/llama2-webui
Run any Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Use `llama2-wrapper` as your local llama2 backend for Generative Agents/Apps.
Jupyter NotebookMIT
Issues
- 0
Change .env after using pip to install
#88 opened by NytePlus - 0
Gradio Memory Leak Issue
#85 opened by ruizcrp - 1
Very slow generation
#83 opened by jaslatendresse - 0
why i7 8700 is faster than i7 9700
#84 opened by AndreaChiChengdu - 2
The temperature parameter does not seem to work
#74 opened by ibutenko - 0
GPU CUDA not found And HFValidationError
#82 opened by HorrorBest - 5
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge
#80 opened by HougeLangley - 5
- 0
- 0
How to add llama_index in llama-webui
#75 opened by Kashif-Inam - 3
GGML deprecated - support GGUF models?
#72 opened by agilebean - 1
Unable to load 70B llama2 on cpu (llama cpp)
#66 opened by Dougie777 - 5
Cant seem to run it on GPU
#50 opened by rishabh-gurbani - 1
Error in text generation, major error
#36 opened by Lyn4ever29 - 1
Is there a plan to support Windows?
#31 opened by tony2u - 4
ERROR. How to fix ?
#67 opened by oaefou - 1
How to run on GPU? Runs on CPU only
#68 opened by oaefou - 1
chat too slow!
#69 opened by Hyingerrr - 6
AssertionError self.model is not None
#70 opened by ebdavison - 8
model is not None
#71 opened by quanpinjie - 2
[FEATURE] docker support
#20 opened by liltom-eth - 2
- 1
OSError: [Errno 30] Read-only file system
#59 opened by realAbitbol - 0
[Feature Request] Support InternLM
#62 opened by vansinhu - 2
Ignores new query and responds with crossed out details (from previous question).
#54 opened by THREELabs - 3
cannot run Llama-2-70b-hf
#53 opened by takitsuba - 2
- 4
- 1
[FEATURE] support for ctransformers
#47 opened by touchtop - 2
[FEATURE] add `--iter` argument for benchmark
#33 opened by liltom-eth - 2
[FEATURE] export conversation as json
#35 opened by roflmao - 1
- 0
[FEATURE] command line app: `cli.py`
#26 opened by liltom-eth - 0
[FEATURE] host a CPU UI in huggingface.
#23 opened by liltom-eth - 1
- 6
CUDA not found
#1 opened by jlb1504 - 6
loading ggmlv3.q4 and q4_K_M
#3 opened by step21 - 6
bitsandbytes can not run on windows10
#4 opened by MrBean818 - 7
- 6
Test log | Welcome to communicate
#9 opened by XksA-me - 3
FileNotFoundError: No such file or directory: "/mnt/Llama-2-13b-chat-hf/model-00001-of-00003.safetensors"
#7 opened by XksA-me - 4
- 0
[FEATURE] support llama2.c
#16 opened by liltom-eth - 1
[FEATURE] Chinese Llama2
#15 opened by liltom-eth - 0
[FEATURE] all in one install script
#13 opened by liltom-eth - 2
Enable share on gradio?
#2 opened by jlb1504