Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / liltom-eth/llama2-webui issues and pull requests

#88 - Change .env after using pip to install

Issue - State: open - Opened by NytePlus 3 months ago

#86 - Update README.md

Pull Request - State: closed - Opened by RISHIKREDDYL 8 months ago - 1 comment

#85 - Gradio Memory Leak Issue

Issue - State: open - Opened by ruizcrp 8 months ago

#84 - why i7 8700 is faster than i7 9700

Issue - State: open - Opened by AndreaChiChengdu 9 months ago

#83 - Very slow generation

Issue - State: open - Opened by jaslatendresse 9 months ago - 1 comment

#82 - GPU CUDA not found And HFValidationError

Issue - State: open - Opened by HorrorBest 10 months ago

#78 - multi gpu, llama2-70b

Pull Request - State: open - Opened by fo40225 10 months ago

#77 - dom.js:238 Uncaught (in promise) DOMException

Issue - State: open - Opened by kisseternity 11 months ago

#76 - [FEATURE] added prompts templates.

Pull Request - State: closed - Opened by BobCN2017 11 months ago - 2 comments

#75 - How to add llama_index in llama-webui

Issue - State: open - Opened by Kashif-Inam 11 months ago

#74 - The temperature parameter does not seem to work

Issue - State: open - Opened by ibutenko 11 months ago - 2 comments

#73 - [FEATURE] add support for GGUF models

Pull Request - State: closed - Opened by liltom-eth 12 months ago

#72 - GGML deprecated - support GGUF models?

Issue - State: closed - Opened by agilebean 12 months ago - 3 comments

#71 - model is not None

Issue - State: closed - Opened by quanpinjie 12 months ago - 8 comments

#70 - AssertionError self.model is not None

Issue - State: closed - Opened by ebdavison 12 months ago - 6 comments

#69 - chat too slow!

Issue - State: closed - Opened by Hyingerrr about 1 year ago - 1 comment

#68 - How to run on GPU? Runs on CPU only

Issue - State: closed - Opened by oaefou about 1 year ago - 1 comment

#67 - ERROR. How to fix ?

Issue - State: closed - Opened by oaefou about 1 year ago - 4 comments

#66 - Unable to load 70B llama2 on cpu (llama cpp)

Issue - State: open - Opened by Dougie777 about 1 year ago - 1 comment

#65 - [DOCUMENT] update readme

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#64 - [DOCUMENT] update readme

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#63 - [FEATURE] Add code llama, add code completion

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#62 - [Feature Request] Support InternLM

Issue - State: open - Opened by vansinhu about 1 year ago

#61 - [FEATURE] Add model downloading script

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#60 - [FEATURE] update app.py with args, test codellama

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#59 - OSError: [Errno 30] Read-only file system

Issue - State: open - Opened by realAbitbol about 1 year ago - 1 comment

#58 - [BUG] bug resolved on fast api

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#57 - [BUILD] Create release.yml for PYPI

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#56 - [FEATURE] add OpenAI compatible API

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#55 - [BUILD] Create branch.yml for CI

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#53 - cannot run Llama-2-70b-hf

Issue - State: closed - Opened by takitsuba about 1 year ago - 3 comments

#52 - [FEATURE] add streaming for call

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#51 - Create read1

Pull Request - State: closed - Opened by nephp06 about 1 year ago

#50 - Cant seem to run it on GPU

Issue - State: closed - Opened by rishabh-gurbani about 1 year ago - 5 comments

#49 - [FEATURE] add args for benchmark

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#48 - When I was running app. py, I encountered some errors

Issue - State: closed - Opened by 15899885850 about 1 year ago - 2 comments

#47 - [FEATURE] support for ctransformers

Issue - State: closed - Opened by touchtop about 1 year ago - 1 comment

#46 - [BUILD] update poetry

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#45 - [FEATURE] Update env

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#44 - [FEATURE] update default model path

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#43 - [BUILD] update poetry

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#42 - [FEATURE] Update requirements

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#41 - [FEATURE] add download model for default

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#40 - [DOCUMENT] update readme, news, performance

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#39 - [DOCUMENT] update reademe, poetry for llama2-wrapper

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#38 - [FEATURE] Llama2 wrapper unify arguments, change initial method

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#37 - ERROR: Failed building wheel for llama-cpp-python

Issue - State: open - Opened by qinshuaibo about 1 year ago - 2 comments

#36 - Error in text generation, major error

Issue - State: closed - Opened by Lyn4ever29 about 1 year ago - 1 comment

#35 - [FEATURE] export conversation as json

Issue - State: open - Opened by roflmao about 1 year ago - 2 comments

#34 - [FEATURE] Added iterations to most parts of the benchmark + Memory usage

Pull Request - State: closed - Opened by jules552 about 1 year ago - 1 comment

#33 - [FEATURE] add `--iter` argument for benchmark

Issue - State: closed - Opened by liltom-eth about 1 year ago - 2 comments

#32 - [DOCUMENT] benchmark: AMD Ryzen 9 5900HS

Pull Request - State: closed - Opened by jules552 about 1 year ago - 2 comments

#31 - Is there a plan to support Windows?

Issue - State: closed - Opened by tony2u about 1 year ago - 1 comment

#30 - [DOCUMENT] Add benchmarks of `i7-9700` and `GTX-1660 Super`

Pull Request - State: closed - Opened by smithlai about 1 year ago

#29 - [DOCUMENT] benchmark: add vserver

Pull Request - State: closed - Opened by step21 about 1 year ago - 2 comments

#28 - [DOCUMENT] update performance

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#27 - [FEATURE] Is there any way to expose this as Rest API instead of Default UI

Issue - State: closed - Opened by ajasingh about 1 year ago - 5 comments

#26 - [FEATURE] command line app: `cli.py`

Issue - State: open - Opened by liltom-eth about 1 year ago

#25 - [Question]: Nice job, we build a webui to use llama2

Issue - State: open - Opened by csunny about 1 year ago - 1 comment

#23 - [FEATURE] host a CPU UI in huggingface.

Issue - State: open - Opened by liltom-eth about 1 year ago

#22 - [FEATURE] add benchmark tokens.sec

Pull Request - State: closed - Opened by liltom-eth about 1 year ago - 1 comment

#20 - [FEATURE] docker support

Issue - State: open - Opened by liltom-eth about 1 year ago - 2 comments

#19 - [FEATURE] Llama2 wrapper generate, __call__ func

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#18 - [FEATURE] Llama2 wrapper

Pull Request - State: closed - Opened by liltom-eth about 1 year ago

#17 - Why can llama understand Chinese so much and can't reply directly in Chinese?

Issue - State: open - Opened by XksA-me about 1 year ago - 4 comments

#16 - [FEATURE] support llama2.c

Issue - State: open - Opened by liltom-eth about 1 year ago

#15 - [FEATURE] Chinese Llama2

Issue - State: open - Opened by liltom-eth about 1 year ago - 1 comment

#14 - [FEATURE] benchmarking script for `tokens / sec`

Issue - State: closed - Opened by liltom-eth about 1 year ago - 1 comment

#13 - [FEATURE] all in one install script

Issue - State: open - Opened by liltom-eth about 1 year ago

#12 - User Chinese-Llama-2-7b.ggmlv3.q4_1.bin Model UnicodeDecodeError: 'utf-8'

Issue - State: open - Opened by xyz-dev about 1 year ago - 4 comments

#11 - huggingface_hub.utils._validators.HFValidationError on CPU

Issue - State: closed - Opened by blackhawkee about 1 year ago - 7 comments

#10 - [DOCUMENT] add performance

Pull Request - State: closed - Opened by minghaoBD about 1 year ago - 1 comment

#9 - Test log | Welcome to communicate

Issue - State: open - Opened by XksA-me about 1 year ago - 6 comments

#8 - [DOCUMENT] update license, intro

Pull Request - State: closed - Opened by AndyW-llm about 1 year ago - 1 comment

#6 - Update README.md

Pull Request - State: closed - Opened by ysx1223 about 1 year ago

#5 - [DOCUMENT] update README.md for Windows dependencies

Pull Request - State: closed - Opened by kemalariboga about 1 year ago - 2 comments

#4 - bitsandbytes can not run on windows10

Issue - State: closed - Opened by MrBean818 about 1 year ago - 6 comments

#3 - loading ggmlv3.q4 and q4_K_M

Issue - State: closed - Opened by step21 about 1 year ago - 6 comments

#2 - Enable share on gradio?

Issue - State: closed - Opened by jlb1504 about 1 year ago - 2 comments

#1 - CUDA not found

Issue - State: closed - Opened by jlb1504 about 1 year ago - 6 comments