Pinned Repositories
AB-Testing
A/B Testing — A complete guide to statistical testing
AB-Testing-For-Mobile-Games
A/B Testing
amExpert_ML_Hackathon_2019_Winners_Soultions
Apriori
Implementation of Market Basket Analysis
Batch202223
creek
生成模型 tokenizer训练，模型初始化，模型预训练，指令微调。llama，creek
CUDA-Learn-Notes
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
JsDecrypt
Js 代码逆向, soJson_v5 代码还原
Nvidia-cuda
learning cuda by nvidia
WSDM-CUP-2022-Retention-Score-Prediction
WSDM2022留存预测挑战赛 第1名解决方案
fisheeped's Repositories
fisheeped/creek
生成模型 tokenizer训练，模型初始化，模型预训练，指令微调。llama，creek
fisheeped/CUDA-Learn-Notes
🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.
fisheeped/AB-Testing
A/B Testing — A complete guide to statistical testing
fisheeped/AB-Testing-For-Mobile-Games
A/B Testing
fisheeped/BigDataTraining
大数据综合项目实训
fisheeped/ChatGLM-LoRA-RLHF-PyTorch
A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically ChatGPT but with ChatGLM
fisheeped/ChatGLM-RLHF
对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF
fisheeped/ChatGLM2-6B-Explained
ChatGLM2-6B-Explained
fisheeped/chatglm2_finetuning
chatglm2 6b finetuning and alpaca finetuning
fisheeped/Chatglm_lora_multi-gpu
chatglm多gpu用deepspeed和
fisheeped/Chinese-Llama-2-7b
开源社区第一个能下载、能运行的中文 LLaMA2 模型！
fisheeped/Chinese-Vicuna
Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca
fisheeped/fisheeped
awaw
fisheeped/flink-kubernetes-operator
Apache Flink Kubernetes Operator
fisheeped/flink1.13
Apache Flink
fisheeped/LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code.
fisheeped/learning
fisheeped/mydocker
mydocker
fisheeped/Open-Llama
The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.
fisheeped/openai-proxy
基于 Go 实现的 OpenAI HTTP 代理（云函数、lambda 函数、自己部署均可）
fisheeped/openserp
Get Google, Yandex, Baidu search engine results via API or CLI for free 🎉
fisheeped/practice_bigdata
博客
fisheeped/sd_lora
Using Low-rank adaptation to quickly fine-tune diffusion models.
fisheeped/sentencepiece_chinese_bpe
使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。
fisheeped/tranformers-code-explained--line-by-line
tranformers-code-explained--line-by-line
fisheeped/transformers4.30.2
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
fisheeped/transformers_tasks
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
fisheeped/tutorial-multi-gpu
Efficient Distributed GPU Programming for Exascale, an SC/ISC Tutorial
fisheeped/visual-openllm
something like visual-chatgpt, 文心一言的开源版
fisheeped/wechatbot
为个人微信接入ChatGPT