MSBD6000N_Understanding_Large_Language_Models

The Project Codes for MSBD 6000N

https://github.com/HKUST-Franky/MSBD6000N_Understanding_Large_Language_Models

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (3.6%) to scientific vocabulary

Last synced: 6 months ago · JSON representation ·

Repository

The Project Codes for MSBD 6000N

Basic Info

Host: GitHub
Owner: HKUST-Franky
License: apache-2.0
Language: Python
Default Branch: main
Size: 236 MB

Statistics

Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created over 1 year ago · Last pushed about 1 year ago

Metadata Files

Readme License Citation

README.md

PersonaCraft Project Codespace

The 6000N Project Files are implemented using the open-source training framework LLaMA Factory.

Pre-processed Datasets

/wxh_scripts/*.py
/data/RoleBench
/data/rolellm_*.json
/data/identity_wxh.json
RoleBench: https://huggingface.co/datasets/ZenMoore/RoleBench ## Evaluation Results
/saves/Llama-3.1-8B-Instruct/lora/*

Training Logs and Adpators

/src/saves/Llama-3.1-8B-Instruct/lora/2024-11-26-14-59-53_dpo
/src/saves/Llama-3.1-8B-Instruct/lora/train_2024-11-26-03-03-10 https://huggingface.co/FrankyCN/PersonaCraft/tree/main/Llama-3.1-8B-Instruct/lora

Models used

https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct

Owner

Name: WU FUNG Xian Hong
Login: HKUST-Franky
Kind: user
Location: Hong Kong
Company: HKUST

Website: https://hkust.edu.hk/
Repositories: 1
Profile: https://github.com/HKUST-Franky

MSc in Big Data Technology at HKUST

Citation (CITATION.cff)

cff-version: 1.2.0
date-released: 2024-03
message: "If you use this software, please cite it as below."
authors:
- family-names: "Zheng"
  given-names: "Yaowei"
- family-names: "Zhang"
  given-names: "Richong"
- family-names: "Zhang"
  given-names: "Junhao"
- family-names: "Ye"
  given-names: "Yanhan"
- family-names: "Luo"
  given-names: "Zheyan"
- family-names: "Feng"
  given-names: "Zhangchi"
- family-names: "Ma"
  given-names: "Yongqiang"
title: "LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models"
url: "https://arxiv.org/abs/2403.13372"
preferred-citation:
  type: conference-paper
  conference:
    name: "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)"
  authors:
    - family-names: "Zheng"
      given-names: "Yaowei"
    - family-names: "Zhang"
      given-names: "Richong"
    - family-names: "Zhang"
      given-names: "Junhao"
    - family-names: "Ye"
      given-names: "Yanhan"
    - family-names: "Luo"
      given-names: "Zheyan"
    - family-names: "Feng"
      given-names: "Zhangchi"
    - family-names: "Ma"
      given-names: "Yongqiang"
  title: "LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models"
  url: "https://arxiv.org/abs/2403.13372"
  year: 2024
  publisher: "Association for Computational Linguistics"
  address: "Bangkok, Thailand"

GitHub Events

Total

Last Year

Dependencies

pyproject.toml pypi

requirements.txt pypi

accelerate >=0.30.1,<=0.34.2
av *
datasets >=2.16.0,<=2.21.0
einops *
fastapi *
fire *
gradio >=4.0.0
matplotlib >=3.7.0
numpy <2.0.0
packaging *
pandas >=2.0.0
peft >=0.11.1,<=0.12.0
protobuf *
pydantic *
pyyaml *
scipy *
sentencepiece *
sse-starlette *
tiktoken *
transformers >=4.41.2,<=4.45.2
trl >=0.8.6,<=0.9.6
uvicorn *

setup.py pypi

src/llamafactory.egg-info/requires.txt pypi

accelerate <=0.34.2,>=0.30.1
adam-mini *
aqlm >=1.1.0
auto-gptq >=0.5.0
autoawq *
av *
badam >=1.2.1
bitsandbytes >=0.39.0
datasets <=2.21.0,>=2.16.0
decorator *
deepspeed <=0.14.4,>=0.10.0
eetq *
einops *
fastapi *
fire *
galore-torch *
gradio >=4.0.0
hqq *
jieba *
liger-kernel *
matplotlib >=3.7.0
modelscope *
nltk *
numpy <2.0.0
optimum >=1.17.0
packaging *
pandas >=2.0.0
peft <=0.12.0,>=0.11.1
protobuf *
pydantic *
pytest *
pyyaml *
rouge-chinese *
ruff *
scipy *
sentencepiece *
sse-starlette *
tiktoken *
torch >=1.13.1
torch ==2.1.0
torch-npu ==2.1.0.post3
transformers <=4.45.2,>=4.41.2
transformers_stream_generator *
trl <=0.9.6,>=0.8.6
uvicorn *
vllm <=0.6.2,>=0.4.3

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science