LLMSurvey
ChatGLM2-6B
| LLMSurvey | ChatGLM2-6B | |
|---|---|---|
| 3 | 4 | |
| 8,902 | 15,514 | |
| 9.2% | 0.9% | |
| 7.9 | 6.6 | |
| 4 months ago | about 1 month ago | |
| Python | Python | |
| - | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
LLMSurvey
-
Ask HN: Textbook Regarding LLMs
Here’s another one - it’s older but has some interesting charts and graphs.
https://arxiv.org/abs/2303.18223
-
Share your favorite materials: intersection of LLMs and business applications
There have recently been some some nice early surveys on progress, pitfalls, future research directions:
- A Survey of LLMs https://arxiv.org/abs/2303.18223
- A Survey of Large Language Models
ChatGLM2-6B
- Are We Overlooking China's Progress in AI?
-
A new open-source language model claims to have surpassed GPT-4 right now. This needs to be fact-checked
If its benchmark results, eg on MMLU few-shot, hold and are indicative of its actual performance (which, mind you, isn't a given, for 6B nor for 130B), this 6B should be competitive with decent 30Bs. Plus natively long context and MQA. This is genuinely interesting, unlike boomer noises about CCP poisoning our checkpoints or whatever.
What are some alternatives?
mPLUG-Owl - mPLUG-Owl & mPLUG-Owl2: Modularized Multimodal Large Language Model
PentestGPT - A GPT-empowered penetration testing tool
Chinese-LLaMA-Alpaca - 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
HugNLP - CIKM2023 Best Demo Paper Award. HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊
gpt_academic - 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
safe-rlhf - Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
inference - Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.
Qwen - The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
llm-gateway - Gateway for secure & reliable communications with OpenAI and other LLM providers
opening-up-chatgpt.github.io - Tracking instruction-tuned LLM openness. Paper: Liesenfeld, Andreas, Alianda Lopez, and Mark Dingemanse. 2023. “Opening up ChatGPT: Tracking Openness, Transparency, and Accountability in Instruction-Tuned Text Generators.” In Proceedings of the 5th International Conference on Conversational User Interfaces. doi:10.1145/3571884.3604316.
DoctorGLM - 基于ChatGLM-6B的中文问诊模型