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.

liltom-eth/llama2-webui Issues

Change .env after using pip to install
Updated 5 months ago
Gradio Memory Leak Issue
Updated 10 months ago
Very slow generation
Updated a year ago1
why i7 8700 is faster than i7 9700
Updated a year ago
The temperature parameter does not seem to work
Updated a year ago2
GPU CUDA not found And HFValidationError
Updated a year ago
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge
Closed a year ago5
[FEATURE] Is there any way to expose this as Rest API instead of Default UI
Closed a year ago5
dom.js:238 Uncaught (in promise) DOMException
Updated a year ago
How to add llama_index in llama-webui
Updated a year ago
GGML deprecated - support GGUF models?
Closed a year ago3
Unable to load 70B llama2 on cpu (llama cpp)
Updated a year ago1
Cant seem to run it on GPU
Closed a year ago5
Error in text generation, major error
Closed a year ago1
Is there a plan to support Windows?
Closed a year ago1
ERROR. How to fix ?
Closed a year ago4
How to run on GPU? Runs on CPU only
Closed a year ago1
chat too slow!
Closed a year ago1
AssertionError self.model is not None
Closed a year ago6
model is not None
Closed a year ago8
[FEATURE] docker support
Updated a year ago2
ERROR: Failed building wheel for llama-cpp-python
Updated a year ago2
OSError: [Errno 30] Read-only file system
Updated a year ago1
[Feature Request] Support InternLM
Updated a year ago
Ignores new query and responds with crossed out details (from previous question).
Closed a year ago2
cannot run Llama-2-70b-hf
Closed a year ago3
When I was running app. py, I encountered some errors
Closed a year ago2
User Chinese-Llama-2-7b.ggmlv3.q4_1.bin Model UnicodeDecodeError: 'utf-8'
Updated a year ago4
[FEATURE] support for ctransformers
Closed a year ago1
[FEATURE] add `--iter` argument for benchmark
Closed a year ago2
[FEATURE] export conversation as json
Updated a year ago2
[Question]: Nice job, we build a webui to use llama2
Updated a year ago1
[FEATURE] command line app: `cli.py`
Updated a year ago
[FEATURE] host a CPU UI in huggingface.
Updated a year ago
[FEATURE] benchmarking script for `tokens / sec`
Closed a year ago1
CUDA not found
Closed a year ago6
loading ggmlv3.q4 and q4_K_M
Closed a year ago6
bitsandbytes can not run on windows10
Closed a year ago6
huggingface_hub.utils._validators.HFValidationError on CPU
Closed a year ago7
Test log | Welcome to communicate
Updated a year ago6
FileNotFoundError: No such file or directory: "/mnt/Llama-2-13b-chat-hf/model-00001-of-00003.safetensors"
Updated a year ago3
Why can llama understand Chinese so much and can't reply directly in Chinese?
Updated a year ago4
[FEATURE] support llama2.c
Updated a year ago
[FEATURE] Chinese Llama2
Updated a year ago1
[FEATURE] all in one install script
Updated a year ago
Enable share on gradio?
Closed a year ago2