Introduction to Qianfan Llama 2 Chinese enhancement technology--SFT, pre-training, instruction optimization - Code World

Introduction to Qianfan Llama 2 Chinese enhancement technology--SFT, pre-training, instruction optimization

Enterprise 2023-12-17 10:28:43 views: null

NoSuchKey

Guess you like

Origin blog.csdn.net/qq_38998213/article/details/134563269

Introduction to Qianfan Llama 2 Chinese enhancement technology--SFT, pre-training, instruction optimization

LLM-Large Model Training-Step (2)-Pre-training/Pre-Training(1): Full-Param Pre-Training (Full-Param Pre-Training) [Full parameter pre-training for LLaMA and other models] [Chinese unsupervised learning corpus 】

Llama2-Chinese project: 2.1-Atom-7B pre-training

LLMs: LLaMA Efficient Tuning (an efficient tool that can efficiently fine-tune [full parameters/LoRA/QLoRA] mainstream large models [ChatGLM2/LLaMA2/Baichuan, etc.] [pre-training + instruction supervision fine-tuning +

[LLM Data] Pre-training data set + instruction to generate sft data set

LLM-large model training-step (2)-pre-training/Pre-Training (2): heavy parameter pre-training (Part-Param Pre-Training) [Lora/ptuning...] [Chinese unsupervised learning corpus]

Chinese Pre-training Model Generalization Ability Challenge (Part 2): Top score skills

Innovative OCR structured technology application, Baidu Chinese and English OCR structured model StrucTexT pre-training model

The Chinese in the Llama 2 team

The largest Llama open source community in China releases the first pre-trained Chinese version Llama2

Bloom&LLAMA of the large model----Pre-Training (secondary pre-training)

Some nice work on Chinese LLaMA2

LLM-Large Model Training-Step (2)-Pre-training/Pre-Training(1): Full-Param Pre-Training (Full-Param Pre-Training) [Full parameter pre-training for LLaMA and other models] [Chinese unsupervised learning corpus 】

LLM-Large Model Training-Step (2)-Pre-training/Pre-Training(1): Full-Param Pre-Training (Full-Param Pre-Training) [Full parameter pre-training for LLaMA and other models] [Chinese unsupervised learning corpus 】

LLM-Large Model Training-Step (2)-Pre-training/Pre-Training(1): Full-Param Pre-Training (Full-Param Pre-Training) [Full parameter pre-training for LLaMA and other models] [Chinese unsupervised learning corpus 】

Firefly-LLaMA2-Chinese - Open source Chinese LLaMA2 large model

PTM of AI: Summary and progress of pre-training model technology (updating)

The self-generated instruction framework Self-Instruct realizes the pre-training language model and instruction alignment (including practical operation + code)

Interpretation and fine-tuning of LLaMA: Alpaca-LoRA/Vicuna/BELLE/Chinese LLaMA/Jiang Ziya/LLaMA 2

Train your own Llama 2! Introduction to large model fine-tuning technology

Chinese-LLaMA-Alpaca-2 of LLMs: source code interpretation (run_clm_pt_with_peft.py file) - model training pre-work (parameter analysis + configuration log) → model initialization (detecting whether there is a trained chec

Chinese pre-training model ERNIE2.0 model download and install

Chinese NLP strongest pre-training model Aini ERNIE Official Secret Annex [video]

Chinese pre-training model ERNIE2.0 model download and install

ELECTRA Chinese pre-training model of open source, 110 parameters, performance comparable BERT

Remember a little white tuning baseline-NLP Chinese pre-training model generalization ability competition

Simple application of BERT pre-training model (Chinese sentence vector correlation analysis)

[Video] The strongest Chinese NLP pre-training model that surpasses BERT Aini ERNIE official secret

[Study Notes] Summary of Research on Open Source Chinese Dialogue Pre-training Model

System Architecture-2-3 Optimization of Instruction Opcodes: Huffman Coding

Recommended

Ranking

SpringBoot entry and the advantages and disadvantages

idea maven report system omitted for duplicate solutions

StackOverflow error when casting to a superclass

2019-06-06 Elastic products Compatibility

springcloud gateway集成oauth2.0

HTTP Headers的Request Headers

js declares arrays and adds object variables to arrays

Nginx summary (c) port-based virtual host configuration

6 Best Practices for Contract Management

Codeforces Round #631 (Div. 2)

Daily

More

2025-03-23(0)

2025-03-22(0)

2025-03-21(0)

2025-03-20(0)

2025-03-19(0)

2025-03-18(0)

2025-03-17(0)

2025-03-16(0)

2025-03-15(0)

2025-03-14(0)