Ecosyste.ms: Awesome

https://github.com/jackfsuia/shampoosalesagent

A minimal LLM sales agent framework for sales agent fast deployment and benchmark. Support OpenAI models, Claude, HuggingFace models, Gemini, Ernie(文心一言4.0), Baichuan(百川), Qwen(通义千问), Moonshot(月之暗面), GLM(智谱), Deepseek. AI销售智能体微型框架.

agent ai framework gpt llm machine-learning nlp recommendation-system retail salesperson selling-platform shampoo shopping

Last synced: 14 Nov 2024

https://github.com/jackfsuia/llm-data-cleaner

用大模型批量处理数据，现支持各种大模型做OCR，支持通义千问, 月之暗面, 百度飞桨OCR, OpenAI 和LLAVA。Use LLM to generate or clean data for academic use. Support OCR with qwen, moonshot, PaddleOCR, OpenAI, Llava.

dataset llm ocr

Last synced: 14 Nov 2024

https://github.com/jackfsuia/vecparser

Vectorize the Matlab/CVX for-loops as much as possible. 自动向量化Matlab和CVX的for循环。

cone convex cvx cvxopt cvxpy lexer matlab matlab-script modeling-and-simulation octave optimization parser python-script vectorization

Last synced: 14 Nov 2024

https://github.com/jackfsuia/proactive-sales-agent

Proactive LLM sales agent server. 主动销售的大模型销售代理服务器。

Last synced: 14 Nov 2024

https://github.com/jackfsuia/phi-3-dpo

a Phi-3 DPO training script. Phi-3 DPO训练脚本

Last synced: 14 Nov 2024

https://github.com/jackfsuia/byllm

一个简易的大模型互评框架，支持批量评测。A mini LLM evaluation framework that supports batch and mutual evaluation.

Last synced: 14 Nov 2024

https://github.com/jackfsuia/chats-crawler

Discourse chat data crawling and on-the-way parsing straight for LLM instruction finetuning. Data include texts, images and links ( Discourse论坛对话（图片，文本）数据爬取并解析，以直接用于（多模态）指令微调).

crawler fine-tuning finetune-llm gpt html-css-javascript instruction-tuning llm llm-training llms nlp nlp-parsing parser

Last synced: 14 Nov 2024

https://github.com/jackfsuia/cvx-coder

LLM good at answering questions and coding about Matlab CVX. 微调大模型写CVX代码，回答CVX问题。

cvx llm matlab

Last synced: 14 Nov 2024

https://github.com/jackfsuia/ragtoolbox

Grab-and-go RAG operators.

llm nlp rag retrieval retrieval-augmented-generation

Last synced: 14 Nov 2024

https://github.com/jackfsuia/open-m1

A roadmap to reproduce OpenAI o1, Combining PRM and RLHF to train the model to learn infinite CoT (Chain of Thought).

chatgpt llm openai-o1 reinforcement-learning strawberry

Last synced: 30 Oct 2024