update open llm

README.md

@@ -10,6 +10,7 @@
   - [Other Papers](#other-papers)
   - [LLM Leaderboard](#llm-leaderboard)
   - [LLM Training Frameworks](#llm-training-frameworks)
+  - [Open LLM](#open-llm)
   - [Tools for deploying LLM](#tools-for-deploying-llm)
   - [Tutorials about LLM](#tutorials-about-llm)
   - [Courses about LLM](#courses-about-llm)
@@ -69,9 +70,9 @@ If you're interested in the field of LLM, you may find the above list of milesto
 
 (:exclamation: **We would greatly appreciate and welcome your contribution to the following list. :exclamation:**)
 
-- [LLM-Evaluation](paper_list/evaluation.md)
+- [LLM-Analysis](paper_list/evaluation.md)
 
-  > Evaluate different LLMs including ChatGPT in different fields
+  > Analyse different LLMs in different fields with respect to different abilities
 
 - [LLM-Acceleration](paper_list/acceleration.md)
 
@@ -84,11 +85,15 @@ If you're interested in the field of LLM, you may find the above list of milesto
 - [LLM-Augmentation](paper_list/augmentation.md)
 
   > Augment LLM in different aspects including faithfulness, expressiveness, domain-specific knowledge etc.
-  
+
 - [LLM-Detection](paper_list/detection.md)
 
   > Detect LLM-generated text from texts written by humans
 
+- [LLM-Alignment](paper_list/alignment.md)
+
+  > Align LLM with Human Preference
+
 - [Chain-of-Thought](paper_list/chain_of_thougt.md)
 
   > Chain of thought—a series of intermediate reasoning steps—significantly improves the ability of large language models to perform complex reasoning.
@@ -97,10 +102,6 @@ If you're interested in the field of LLM, you may find the above list of milesto
 
   > Large language models (LLMs) demonstrate an in-context learning (ICL) ability, that is, learning from a few examples in the context.
 
-- [RLHF](paper_list/RLHF.md)
-
-  > Reinforcement Learning from Human Preference
-
 - [Prompt-Learning](paper_list/prompt_learning.md)
 
   > A Good Prompt is Worth 1,000 Words
@@ -174,6 +175,31 @@ The following list makes sure that all LLMs are compared **apples to apples**.
 
 ---
 
+## Open LLM
+
+- [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) - A foundational, 65-billion-parameter large language model. [LLaMA.cpp](https://github.com/ggerganov/llama.cpp) [Lit-LLaMA](https://github.com/Lightning-AI/lit-llama)
+  - [Alpaca](https://crfm.stanford.edu/2023/03/13/alpaca.html) - A model fine-tuned from the LLaMA 7B model on 52K instruction-following demonstrations. [Alpaca.cpp](https://github.com/antimatter15/alpaca.cpp) [Alpaca-LoRA](https://github.com/tloen/alpaca-lora)
+  - [Flan-Alpaca](https://github.com/declare-lab/flan-alpaca) - Instruction Tuning from Humans and Machines.
+  - [Baize](https://github.com/project-baize/baize-chatbot) - Baize is an open-source chat model trained with [LoRA](https://github.com/microsoft/LoRA). It uses 100k dialogs generated by letting ChatGPT chat with itself. 
+  - [Cabrita](https://github.com/22-hours/cabrita) - A portuguese finetuned instruction LLaMA.
+  - [Vicuna](https://github.com/lm-sys/FastChat) - An Open-Source Chatbot Impressing GPT-4 with 90% ChatGPT Quality. 
+  - [Chinese-Vicuna](https://github.com/Facico/Chinese-Vicuna) - A Chinese Instruction-following LLaMA-based Model.
+  - [GPTQ-for-LLaMA](https://github.com/qwopqwop200/GPTQ-for-LLaMa) - 4 bits quantization of [LLaMA](https://arxiv.org/abs/2302.13971) using [GPTQ](https://arxiv.org/abs/2210.17323).
+  - [GPT4All](https://github.com/nomic-ai/gpt4all) - Demo, data, and code to train open-source assistant-style large language model based on GPT-J and LLaMa.
+  - [Koala](https://bair.berkeley.edu/blog/2023/04/03/koala/) - A Dialogue Model for Academic Research
+  - [StackLLaMA](https://huggingface.co/blog/stackllama) - A hands-on guide to train LLaMA with RLHF.
+- [BLOOM](https://huggingface.co/bigscience/bloom) - BigScience Large Open-science Open-access Multilingual Language Model [BLOOM-LoRA](https://github.com/linhduongtuan/BLOOM-LORA)
+- [GLM](https://github.com/THUDM/GLM)- GLM is a General Language Model pretrained with an autoregressive blank-filling objective and can be finetuned on various natural language understanding and generation tasks.
+  - [ChatGLM-6B](https://github.com/THUDM/ChatGLM-6B) - ChatGLM-6B 是一个开源的、支持中英双语的对话语言模型，基于 [General Language Model (GLM)](https://github.com/THUDM/GLM) 架构，具有 62 亿参数.
+- [RWKV](https://github.com/BlinkDL/RWKV-LM) - Parallelizable RNN with Transformer-level LLM Performance.
+  - [ChatRWKV](https://github.com/BlinkDL/ChatRWKV) - ChatRWKV is like ChatGPT but powered by my RWKV (100% RNN) language model.
+- [StableLM](https://stability.ai/blog/stability-ai-launches-the-first-of-its-stablelm-suite-of-language-models) - Stability AI Language Models.
+- [GPT-J](https://github.com/kingoflolz/mesh-transformer-jax/#gpt-j-6b) - A 6 billion parameter, autoregressive text generation model trained on [The Pile](https://pile.eleuther.ai/).
+- [Pythia](https://github.com/EleutherAI/pythia) - Interpreting Autoregressive Transformers Across Time and Scale
+  - [Dolly](https://github.com/databrickslabs/dolly) - Databricks’ [Dolly](https://huggingface.co/databricks/dolly-v2-12b) is an instruction-following large language model trained on the Databricks machine learning platform that is licensed for commercial use.
+- [OpenFlamingo](https://github.com/mlfoundations/open_flamingo) - an open-source reproduction of DeepMind's Flamingo model.
+- [MOSS](https://github.com/OpenLMLab/MOSS) - MOSS是一个支持中英双语和多种插件的开源对话语言模型.
+
 ## LLM Training Frameworks
 
 <div align=center>

paper_list/RLHF.md

@@ -0,0 +1 @@
+## 

paper_list/alignment.md

@@ -0,0 +1,9 @@
+# Alignment
+
+## Papers
+
+### 2023
+
+- (2023-04) **Fundamental Limitations of Alignment in Large Language Models** [paper](https://arxiv.org/abs/2304.11082)
+
+## Useful Resources

paper_list/augmentation.md

@@ -9,5 +9,6 @@
 - (2023-02) **Augmented Language Models: a Survey** [paper](https://arxiv.org/abs/2302.07842)
 - (2023-03) **Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback** [paper](https://arxiv.org/abs/2303.05453)
 - (2023-03) **Reflexion: an autonomous agent with dynamic memory and self-reflection** [paper](https://arxiv.org/abs/2303.11366)
+- (2023-04) **Scaling Transformer to 1M tokens and beyond with RMT** [paper](https://arxiv.org/abs/2304.11062)
 
 ## Useful Resources

paper_list/evaluation.md

@@ -45,5 +45,9 @@
 
 - (2023-03) **ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks** [paper](https://arxiv.org/abs/2303.15056)
 
+- (2023-04) **Emergent and Predictable Memorization in Large Language Models** [paper](https://arxiv.org/abs/2304.11158)
+
+- (2023-04) **Why Does ChatGPT Fall Short in Answering Questions Faithfully?** [paper](https://arxiv.org/abs/2304.10513)
+
 ## Useful Resources