Ecosyste.ms: Summary

An open API service providing a high level summary for open source projects.

awesome-llama: https://github.com/georgian-io/LLM-Finetuning-Toolkit

ablation-study classification falcon fine-tuning finetuning flan-t5 large-language-models llama2 llm-test lora mistral-7b nlp nlp-machine-learning qlora redpajama summarization unit-testing zephyr

Score: 15.522557823259334

Last synced: 6 days ago
JSON representation

Repository metadata:

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.


Owner metadata:


GitHub Events

Total
Last Year

Committers metadata

Last synced: 6 days ago

Total Commits: 420
Total Committers: 19
Avg Commits per committer: 22.105
Development Distribution Score (DDS): 0.576

Commits in past year: 176
Committers in past year: 10
Avg Commits per committer in past year: 17.6
Development Distribution Score (DDS) in past year: 0.256

Name Email Commits
Benjamin Ye b****e@g****o 178
RohitSaha r****7@g****m 68
Ubuntu u****u@i****l 40
Ubuntu u****u@i****l 24
Mariia Ponomarenko m****o@M****l 20
SinclairHudson h****0@g****m 17
Ubuntu u****u@i****l 16
[email protected] m****o@g****o 12
Ubuntu u****u@i****l 9
Vivek Singh 9****S 8
viveksingh-ctrl 8****l 7
Ubuntu u****u@i****l 7
Akash Saravanan a****n@g****o 4
Ubuntu u****u@i****l 4
georgianpoole 1****e 2
Borna Almasi b****a@b****m 1
Kyryl Truskovskyi t****k@g****m 1
Titus 9****r 1
dependabot[bot] 4****] 1

Issue and Pull Request metadata

Last synced: 8 days ago

Total issues: 9
Total pull requests: 97
Average time to close issues: about 1 month
Average time to close pull requests: 10 days
Total issue authors: 7
Total pull request authors: 10
Average comments per issue: 1.78
Average comments per pull request: 0.3
Merged pull request: 80
Bot issues: 0
Bot pull requests: 8

Past year issues: 6
Past year pull requests: 33
Past year average time to close issues: 11 days
Past year average time to close pull requests: 5 days
Past year issue authors: 4
Past year pull request authors: 6
Past year average comments per issue: 1.0
Past year average comments per pull request: 0.24
Past year merged pull request: 26
Past year bot issues: 0
Past year bot pull requests: 4

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/georgian-io/LLM-Finetuning-Toolkit

Top Issue Authors

  • benjaminye (3)
  • viveksingh-ctrl (1)
  • sammcj (1)
  • jeetendraabvv (1)
  • kel-varnsen (1)
  • jerin-scalers-ai (1)
  • charlesmartin14 (1)

Top Pull Request Authors

  • RohitSaha (43)
  • benjaminye (19)
  • mariia-georgian (15)
  • dependabot[bot] (8)
  • VivekSinghDS (6)
  • georgianpoole (2)
  • balmasi (1)
  • SinclairHudson (1)
  • anthonyprinaldi (1)
  • akashsaravanan-georgian (1)

Top Issue Labels

  • enhancement (3)
  • question (3)
  • good first issue (2)
  • bug (1)

Top Pull Request Labels

  • enhancement (11)
  • dependencies (9)
  • documentation (1)
  • bug (1)

Package metadata

pypi.org: llm-toolkit

LLM Finetuning resource hub + toolkit

  • Homepage: https://github.com/georgian-io/LLM-Finetuning-Toolkit
  • Documentation: https://llm-toolkit.readthedocs.io/
  • Licenses: Apache 2.0
  • Latest release: 0.2.3 (published 6 months ago)
  • Last Synced: 2025-01-20T15:24:30.845Z (8 days ago)
  • Versions: 9
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 354 Last month
  • Rankings:
    • Dependent packages count: 9.607%
    • Average: 36.496%
    • Dependent repos count: 63.384%
  • Maintainers (2)

Dependencies

inference/fastapi_naive/Dockerfile docker
  • huggingface/transformers-pytorch-gpu 4.27.2 build
inference/fastapi_naive/requirements.txt pypi
  • bitsandbytes ==0.39.0
  • fastapi ==0.100.0
  • huggingface-hub ==0.16.4
  • numpy ==1.24.3
  • peft ==0.4.0
  • pydantic_settings ==2.0.2
  • scipy ==1.10.1
  • transformers ==4.27.2
  • uvicorn ==0.22.0
requirements.txt pypi
  • absl-py ==1.4.0
  • accelerate ==0.21.0
  • bitsandbytes ==0.39.0
  • datasets ==2.12.0
  • einops ==0.6.1
  • evaluate ==0.4.0
  • ipdb ==0.13.13
  • nltk ==3.8.1
  • numpy ==1.24.3
  • pandas ==2.0.2
  • peft ==0.4.0
  • py7zr ==0.20.5
  • rouge-score ==0.1.2
  • scikit-learn ==1.2.2
  • scipy ==1.10.1
  • tiktoken ==0.4.0
  • transformers ==4.30.1
  • trl ==0.4.7
  • wandb ==0.15.4