Multilingual LLM Adaptation Transformer Models

Tools for adapting and fine-tuning large language models for non-English languages and specific domains/dialects. Includes instruction-tuning, domain-specific pretraining, and language-specific model development. Does NOT include general LLM frameworks, English-only model implementations, or application-specific fine-tuning for tasks like sentiment analysis.

There are 101 multilingual llm adaptation models tracked. 4 score above 50 (established tier). The highest-rated is shibing624/MedicalGPT at 68/100 with 4,948 stars. 2 of the top 10 are actively maintained.

Get all 101 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=transformers&subcategory=multilingual-llm-adaptation&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Model	Score	Tier	Stars	Language
1	shibing624/MedicalGPT MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training...	68	Established	4,948	Python
2	lyogavin/airllm AirLLM 70B inference with single 4GB GPU	67	Established	13,828	Jupyter Notebook
3	GradientHQ/parallax Parallax is a distributed model serving framework that lets you build your...	57	Established	1,152	Python
4	CrazyBoyM/llama3-Chinese-chat Llama3、Llama3.1 中文后训练版仓库 - 微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档。	55	Established	4,154	Python
5	CLUEbenchmark/CLUE 中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets,...	49	Emerging	4,237	Python
6	MediaBrain-SJTU/MING 明医 (MING)：中文医疗问诊大模型	49	Emerging	1,109	Python
7	time-series-foundation-models/lag-llama Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting	49	Emerging	1,556	Python
8	Beomi/KoAlpaca KoAlpaca: 한국어 명령어를 이해하는 오픈소스 언어모델 (KoAlpaca: An open-source language model...	48	Emerging	1,578	Jupyter Notebook
9	X-D-Lab/LangChain-ChatGLM-Webui 基于LangChain和ChatGLM-6B等系列LLM的针对本地知识库的自动问答	48	Emerging	3,307	Python
10	ymcui/Chinese-LLaMA-Alpaca 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)	48	Emerging	18,970	Python
11	AndrewZhe/lawyer-llama 中文法律LLaMA (LLaMA for Chinese legel domain)	48	Emerging	984	Python
12	Facico/Chinese-Vicuna Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model ——...	48	Emerging	4,136	C
13	jackaduma/Recurrent-LLM The open-source LLM implementation of paper: RecurrentGPT: Interactive...	47	Emerging	203	Python
14	xusenlinzy/api-for-open-llm Openai style api for open large language models, using LLMs just as chatgpt!...	47	Emerging	2,468	Python
15	The-FinAI/PIXIU This repository introduces PIXIU, an open-source resource featuring the...	47	Emerging	835	Jupyter Notebook
16	ymcui/Chinese-LLaMA-Alpaca-2 中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs...	47	Emerging	7,163	Python
17	IDEA-CCNL/Fengshenbang-LM Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。	46	Emerging	4,149	Python
18	LianjiaTech/BELLE BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）	46	Emerging	8,284	HTML
19	SCIR-HI/Huatuo-Llama-Med-Chinese Repo for BenTsao [original name: HuaTuo (华驼)], Instruction-tuning Large...	46	Emerging	4,938	Python
20	WangRongsheng/CareGPT 🌞 CareGPT...	46	Emerging	1,009	Python
21	ymcui/Chinese-LLaMA-Alpaca-3 中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3	45	Emerging	1,968	Python
22	baichuan-inc/Baichuan-7B A large-scale 7B pretraining language model developed by BaiChuan-Inc.	45	Emerging	5,680	Python
23	CMKRG/QiZhenGPT QiZhenGPT: An Open Source Chinese Medical Large Language Model｜一个开源的中文医疗大语言模型	45	Emerging	770	Python
24	PhoebusSi/Alpaca-CoT We unified the interfaces of instruction-tuning data (e.g., CoT data),...	45	Emerging	2,801	Jupyter Notebook
25	jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese 聚宝盆(Cornucopia):...	44	Emerging	658	Python
26	ddzipp/AutoAudit AutoAudit—— the LLM for Cyber Security 网络安全大语言模型	43	Emerging	353	HTML
27	WangRongsheng/ChatGenTitle 🌟 ChatGenTitle：使用百万arXiv论文信息在LLaMA模型上进行微调的论文题目生成模型	43	Emerging	840	Python
28	ariannamethod/nanollama Train Llama 3 models from scratch. Any scale, any personality. By Arianna Method.	42	Emerging	37	Python
29	declare-lab/flan-alpaca This repository contains code for extending the Stanford Alpaca synthetic...	42	Emerging	357	Python
30	airaria/Visual-Chinese-LLaMA-Alpaca 多模态中文LLaMA&Alpaca大语言模型（VisualCLA）	41	Emerging	461	Python
31	jianzhnie/awesome-instruction-datasets A collection of awesome-prompt-datasets, awesome-instruction-dataset, to...	40	Emerging	725	—
32	IAAR-Shanghai/Grimoire Grimoire is All You Need for Enhancing Large Language Models	40	Emerging	117	Python
33	MetaGLM/FinGLM FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。	40	Emerging	2,194	HTML
34	ECNU-ICALK/EduChat An open-source educational chat model from ICALK, East China Normal...	40	Emerging	913	Jupyter Notebook
35	HqWu-HITCS/Awesome-Chinese-LLM 整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。	40	Emerging	22,371	—
36	sanjibnarzary/awesome-llm Curated list of open source and openly accessible large language models	40	Emerging	25	—
37	shm007g/LLaMA-Cult-and-More Large Language Models for All, 🦙 Cult and More, Stay in touch !	39	Emerging	452	HTML
38	Nkluge-correa/Tucano Natively pre-trained open-source Portuguese language models.	38	Emerging	79	Jupyter Notebook
39	Longyichen/Alpaca-family-library Summarize all open source Large Languages Models and low-cost replication...	38	Emerging	136	—
40	wenge-research/YAYI 雅意大模型：为客户打造安全可靠的专属大模型，基于大规模中英文多领域指令数据训练的 LlaMA 2 & BLOOM...	38	Emerging	3,051	Python
41	ictnlp/BayLing “百聆”是一个基于LLaMA的语言对齐增强的英语/中文大语言模型，具有优越的英语/中文能力，在多语言和通用任务等多项测试中取得ChatGPT...	38	Emerging	318	Python
42	yangjianxin1/Firefly Firefly:...	37	Emerging	6,644	Python
43	Harish25/StudyScreeningLanguageModel Core LLM for M.A.R.S. (Model Assisted Review System). Utilizes fine-tuned...	37	Emerging	1	Jupyter Notebook
44	CVI-SZU/Linly Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集	37	Emerging	3,056	Python
45	LlamaFamily/Llama-Chinese Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用	37	Emerging	14,737	Python
46	StarRing2022/ChatGPTX-Uni 实现一种多Lora权值集成切换+Zero-Finetune零微调增强的跨模型技术方案，LLM-Base+LLM-X+Alpaca，初期，LLM-Base为...	37	Emerging	116	Python
47	teelinsan/camoscio Camoscio: An Italian instruction-tuned language model based on LLaMA	37	Emerging	126	Jupyter Notebook
48	DAMO-NLP-SG/LLM-Zoo LLM Zoo collects information of various open- and close-sourced LLMs	36	Emerging	271	—
49	robinhad/kruk Ukrainian instruction-tuned language models and datasets	36	Emerging	96	Jupyter Notebook
50	pleisto/yuren-baichuan-7b 基于baichuan-7b的开源多模态大语言模型	36	Emerging	72	Python
51	ChuloAI/BrainChulo Harnessing the Memory Power of the Camelids	36	Emerging	147	Python
52	FSoft-AI4Code/CodeCapybara Open-source Self-Instruction Tuning Code LLM	36	Emerging	172	Python
53	abcsys/libem Compound AI toolchain for fast and accurate entity matching, powered by LLMs.	36	Emerging	26	Python
54	wxjiao/ParroT The ParroT framework to enhance and regulate the Translation Abilities...	35	Emerging	176	Python
55	starmpcc/CAMEL Clinically Adapted Model Enhanced from LLaMA	34	Emerging	89	Python
56	BIDS-Xu-Lab/Me-LLaMA A novel medical large language model family with 13/70B parameters, which...	33	Emerging	167	Python
57	yangjianxin1/Firefly-LLaMA2-Chinese Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、Intern...	32	Emerging	416	Python
58	yaodongC/awesome-instruction-dataset A collection of open-source dataset to train instruction-following LLMs...	32	Emerging	1,145	—
59	Curated-Awesome-Lists/Awesome-Llama3 A curated, awesome list of resources, tools, and projects for the AI Large...	31	Emerging	3	—
60	yeyupiaoling/Chinese-LLM-Chat 大语言模型微调的项目，包含了使用QLora微调ChatGLM和LLama	30	Emerging	28	Python
61	imanslab/poc-uncensored-language-with-wizard-vicuna Uncensored Language Model using FastAPI and Wizard Vicuna 30B (PoC)	30	Emerging	13	Python
62	GaryYufei/AlignLLMHumanSurvey Aligning Large Language Models with Human: A Survey	30	Emerging	741	—
63	DreamerGPT/DreamerGPT 🌱 梦想家(DreamerGPT)：中文大语言模型指令精调	29	Experimental	51	Python
64	nuhmanpk/Awesome-open-LLM Awesome-Open-LLM : a curated list of open-source Large Language Models (LLMs)	29	Experimental	9	—
65	WangRongsheng/Chinese-LLaMA-Alpaca-Usage 📔 对Chinese-LLaMA-Alpaca进行使用说明和核心代码注解	29	Experimental	51	Jupyter Notebook
66	rameshvarun/magic-lamp Magic LLM-powered Python functions that return anything you ask for. Many caveats.	29	Experimental	1	Python
67	GreenScreen410/LYMT LYMT: Let Your Model Think	28	Experimental	4	Python
68	LEL-A/doc Overarching documentation and planning to build so-called...	28	Experimental	10	—
69	CanvaChen/chinese-llama-tokenizer 目标：构建一个更符合语言学的小而美的 llama 分词器，支持中英日三国语言	27	Experimental	20	Python
70	taishan1994/qlora-chinese-LLM 使用qlora对中文大语言模型进行微调，包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE	25	Experimental	89	Python
71	lucataco/cog-llama-3-vision-alpha Cog wrapper for qresearch/llama-3-vision-alpha	25	Experimental	11	Python
72	hululuzhu/llama-lora-chinese-couplet llama-lora e2e example to demo a Chinese Couplet AI in 10 mins. some...	24	Experimental	5	Jupyter Notebook
73	YY0649/ICE-PIXIU ICE-PIXIU：A Cross-Language Financial Megamodeling Framework	22	Experimental	18	Python
74	alta3/llm-the-alta3-way The greatest LLMs on the planet!	22	Experimental	6	Python
75	KnowledgeForge/keymaker The most powerful and extensible way to control the output of large language models.	22	Experimental	6	Python
76	mchl-labs/stambecco The home of Stambecco 🦌: Italian Instruction-following LLaMA Model	22	Experimental	19	Jupyter Notebook
77	eason69113-source/Chat-HuanHuan 基于 Meta-Llama-3.1-8B-Instruct + 4-bit 量化 + QLoRA，训练与推理全程显存占用 < 9 GB，RTX...	21	Experimental	2	Python
78	svjack/Genshin-Impact-Character-Instruction Genshin Impact Character Instruction Models tuned by Lora on LLM	21	Experimental	7	Python
79	declare-lab/flacuna Flacuna was developed by fine-tuning Vicuna on Flan-mini, a comprehensive...	21	Experimental	111	Python
80	iandennismiller/calm A peaceful user experience for Large Language Models. Calm automatically...	20	Experimental	6	Python
81	hello-shohanur/Fine-Tuning-Llama-on-Bengali-Empathetic-Conversations A fine-tuned LLaMA 3.1-8B-Instruct to generate empathetic responses in...	20	Experimental	1	Python
82	s-JoL/Llama3-extend-vocab A demo of expanding the vocabulary of the Llama3 model, applicable to other...	20	Experimental	8	Python
83	lawwu/awesome-llamas Awesome repositories for LLaMA1 and LLaMA2	19	Experimental	18	—
84	MdAliAhnaf/Bengali-Sentiment-Analysis-ML_Fine-Tune-Llama-3.1 Trained and evaluated traditional ML models, fine-tuned Dolphin 2.9.4 based...	18	Experimental	2	Jupyter Notebook
85	FunnySaltyFish/best_llm Vote the Best LLM by yourself! 票选你最喜欢的大语言模型	18	Experimental	2	Python
86	lizhongyi123/llama2_chat_fine 该项目为对llama2进行微调及使用中文微调的技术细节，适合初学者观看。	18	Experimental	23	Python
87	Ljzd-PRO/llm-chat-style-fine-tuning-guide QQ群成员聊天风格大模型LLM微调指引	17	Experimental	1	Python
88	yhinsson/airllm 🚀 Optimize memory for large language models, enabling 70B models on a 4GB...	15	Experimental	2	—
89	RealTapeL/Xiao_i_Chat 用于职业教育领域的大语言模型	13	Experimental	14	Python
90	Maryamm-2/SpeechCueLLM-Amplifying-LLMs-in-Emotion-Recognition-with-Vocal-Nuances SpeechCueLLM Implementation: Enabling Llama-3 to detect emotions from speech...	13	Experimental	—	Jupyter Notebook
91	Mrbysco/LLamaPalooza LlamaPalooza! LlamaPalooza! LlamaPalooza! Yeahh	13	Experimental	—	Java
92	ShoaibSheriff/Cordobesa A specialized RAG-inspired localization pipeline that leverages...	12	Experimental	1	Python
93	mounta11n/VowelReconstruct An easy to use and understand method for the average user to test various...	12	Experimental	6	Python
94	lathashree01/ClinicalRE_n2c2 LLaMA based Clinical RE for n2c2 2018 dataset	11	Experimental	—	Python
95	lucataco/cog-Meta-Llama-Guard-2-8B Cog wrapper for meta-llama/Meta-Llama-Guard-2-8B	11	Experimental	4	Python
96	sacredvoid/ai_clinical_trial Developing a system to match eligible patients to ongoing clinical trials...	11	Experimental	3	Python
97	nlp4se/FeaClustRE_old API for feature clustering, generating hierarchical feature organization...	11	Experimental	1	Python
98	lathashree01/LlamaClinicalRE Llama based clinical RE framework	11	Experimental	—	Jupyter Notebook
99	chaoswork/Awesome-LLaMA A list of awesome projects and resources related to LLaMA LLM	11	Experimental	3	—
100	sadkowsk/codellama-Aug.2023 Learn about "Code Llama: Open Foundation Models for Code" (24 Aug. 2023) by Meta AI.	10	Experimental	2	Jupyter Notebook
101	ghost-x-ai/ghost-8b-beta Ghost 8B Beta is a large language model developed with goals that include...	10	Experimental	2	—

Comparisons in this category

airllm and Chinese-LLaMA-Alpaca (67 vs 48) Chinese-LLaMA-Alpaca and Chinese-LLaMA-Alpaca-2 (48 vs 47) llama3-Chinese-chat and Chinese-LLaMA-Alpaca (55 vs 48)