cabrita
Chinese-LLaMA-Alpaca
| cabrita | Chinese-LLaMA-Alpaca | |
|---|---|---|
| 2 | 4 | |
| 546 | 17,594 | |
| 1.3% | - | |
| 3.1 | 8.3 | |
| 12 months ago | 29 days ago | |
| Jupyter Notebook | Python | |
| Apache License 2.0 | Apache License 2.0 |
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.
cabrita
-
Teaching Llama to reason in another language help!
There was an attempt to teach LLama 1 Portuguese: https://github.com/22-hours/cabrita , and so I used the same dataset on Llama2-13B-chat to update the project, but like some of you have been experiencing, the model goes off its rocker after around 100 tokens, doesn't know when to stop, often lapses into English while still being correct, etc.
-
Its possible to fine tune the llama model to better understand another language?
Portuguese: https://github.com/22-hours/cabrita/
Chinese-LLaMA-Alpaca
-
Chinese-Alpaca-Plus-13B-GPTQ
I'd like to share with you today the Chinese-Alpaca-Plus-13B-GPTQ model, which is the GPTQ format quantised 4bit models of Yiming Cui's Chinese-LLaMA-Alpaca 13B for GPU reference.
-
How to train a new language that is not in base model?
Could follow what people did with the Chinese-LLaMA, just for Korean. Might want to have a pure Korean corpus before feeding in a translation dataset. How big is it by the way?
- Open Source Chinese LLMs
-
Its possible to fine tune the llama model to better understand another language?
Chinese: https://github.com/ymcui/Chinese-LLaMA-Alpaca
What are some alternatives?
KoAlpaca - KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델
ChatGLM2-6B - ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
CodeCapybara - Open-source Self-Instruction Tuning Code LLM
LLMSurvey - The official GitHub page for the survey paper "A Survey of Large Language Models".
paxml - Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.
Qwen-VL - The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.
LLM-Agent-Paper-List - The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
Cornucopia-LLaMA-Fin-Chinese - 聚宝盆(Cornucopia): 中文金融系列开源可商用大模型，并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)
BELLE - BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
llm-leaderboard - A joint community effort to create one central leaderboard for LLMs.
llama.onnx - LLaMa/RWKV onnx models, quantization and testcase
vanilla-llama - Plain pytorch implementation of LLaMA