#LMFlow - Twitter Hashtag

over 2 years ago

#LMFlow now supports the fine-tuning of Qwen2 🤗🚀A SOTA ✅Full-parameter training ✅LoRA ✅QLoRA 🚧LISA: under integration https://t.co/vxBRTKBUeM

Binyuan Hui

@huybery

over 2 years ago

After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you: ⭐ Base and Instruct models of 5 sizes, including Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B, Qwen2-57B-A14B, and Qwen2-72B. Having been trained on data in 27 additional languages besides English and Chinese. 🌟 SOTA performance in a large number of benchmark evaluations. Significantly improved performance in coding and math. 🌠 Extended context length support up to 128K tokens with Qwen2-7B-Instruct and Qwen2-72B-Instruct. 📚 BLOG: https://t.co/qdN92SdUeQ 🤗 DEMO: https://t.co/LS3PxeWSw2 🤖 CODE: https://t.co/dfAfWytdUu

huybery's tweet photo. After months of efforts, we are pleased to announce the evolution from Qwen1.5 to Qwen2. This time, we bring to you:

⭐ Base and Instruct models of 5 sizes, including Qwen2-0.5B, Qwen2-1.5B, Qwen2-7B, Qwen2-57B-A14B, and Qwen2-72B. Having been trained on data in 27 additional languages besides English and Chinese.

🌟 SOTA performance in a large number of benchmark evaluations. Significantly improved performance in coding and math.

🌠 Extended context length support up to 128K tokens with Qwen2-7B-Instruct and Qwen2-72B-Instruct.

📚 BLOG: https://t.co/qdN92SdUeQ
🤗 DEMO: https://t.co/LS3PxeWSw2
🤖 CODE: https://t.co/dfAfWytdUu

63

822

175

269

203K

0

12

3

2

2K

Rui Pan

@rui4research

over 2 years ago

ChatML template is also supported in #LMFlow now 🚀 Just adding --conversation_template chatml and you are all set! 😉 - Example: https://t.co/ilyHIqUEGR - Document: https://t.co/VauKpUZj1b

Maxime Labonne

@maximelabonne

over 2 years ago

🦙 OrpoLlama-3-8B Successful ORPO fine-tune of Llama 3 with ChatML template! It was trained on 40K high-quality preference samples for 3 epochs. Sharing some details and benchmarks. 🧵 🤗 Model: https://t.co/c2sdaskFh6 🪟 Demo: https://t.co/w4z4EdRlsg

maximelabonne's tweet photo. 🦙 OrpoLlama-3-8B

Successful ORPO fine-tune of Llama 3 with ChatML template!

It was trained on 40K high-quality preference samples for 3 epochs. Sharing some details and benchmarks. 🧵

🤗 Model: https://t.co/c2sdaskFh6
🪟 Demo: https://t.co/w4z4EdRlsg

12

215

37

106

47K

0

4

1

2

386

Rui Pan

@rui4research

over 2 years ago

Phi-3 template supported in #LMFlow, waiting for the base model 👀 Try further tuning Phi-3-instruct in LMFlow with SFT/#LISA/#LoRA via 👇

rui4research's tweet photo. Phi-3 template supported in #LMFlow, waiting for the base model 👀

Try further tuning Phi-3-instruct in LMFlow with SFT/#LISA/#LoRA via 👇 https://t.co/bMTEYbhb6j

Sebastien Bubeck

@SebastienBubeck

over 2 years ago

phi-3 is here, and it's ... good :-). I made a quick short demo to give you a feel of what phi-3-mini (3.8B) can do. Stay tuned for the open weights release and more announcements tomorrow morning! (And ofc this wouldn't be complete without the usual table of benchmarks!)

SebastienBubeck's tweet photo. phi-3 is here, and it's ... good :-).

I made a quick short demo to give you a feel of what phi-3-mini (3.8B) can do. Stay tuned for the open weights release and more announcements tomorrow morning!

(And ofc this wouldn't be complete without the usual table of benchmarks!) https://t.co/AWA7Km59rp

39

906

173

291

486K

0

6

1

0

1K

Activ Insights @Activ_Insights

over 3 years ago

🚀 Train your #ChatGPT #LLMs using your 🖥️ #NVIDIA #GPU at #home in just 5 hours! 💪 Supercharge your model development with LMFlow, the ultimate toolkit. #AI #GPT #LMFlow #NvidiaGPU 🎯🔥 Read more: https://t.co/Tq5b5F2M9Y

0

2

0

41

Jenner AI @Jenner_ai

over 3 years ago

🚀 Discover the rising star in AI: LMFlow! Revolutionizing language models and empowering developers. #AI #LMFlow https://t.co/uqWAQ0YzMc

0

2

0

14

OptimalScale @OptimalScale

over 3 years ago

🥳 The LMFlow paper (https://t.co/ojT44dsgrd) has officially dropped! 📚⚡️ ⏩ LMFlow is your go-to toolkit for unleashing the power of LLMs. 🌟✨ 🔎 Dive into the nitty-gritty of our mind-blowing implementation.💥🔥 💻 Let your creativity flow freely! 🌊💡 #LMFlow #LLM #GitHub

0

8

1

2

383

Shizhe Diao @shizhediao

over 3 years ago

@ClementDelangue Our training code and training data are fully open-source (https://t.co/oNIONeY5pe)! Feel free to use LMFlow to fine-tune your own models. #LMFlow #machinelearning

0

3

1

4

457

OptimalScale @OptimalScale

over 3 years ago

🤖💬Evaluating chat-style Large Language Models just got easier with LMFlow benchmark! A free and user-friendly evaluation framework now open-sourced for the entire community. Say goodbye to expensive human labeling and API calls. See https://t.co/z45bxxGCLV 🌟#LMFlow #ChatGPT

OptimalScale's tweet photo. 🤖💬Evaluating chat-style Large Language Models just got easier with LMFlow benchmark! A free and user-friendly evaluation framework now open-sourced for the entire community. Say goodbye to expensive human labeling and API calls. See https://t.co/z45bxxGCLV 🌟#LMFlow #ChatGPT https://t.co/5uWlsI4WbK

5

10

1

3

2K

OptimalScale @OptimalScale

over 3 years ago

Great to announce that LMFlow has launched a gradio demo (LMFlow-chat) in huggingface space! Welcome to try out our latest model Robin-7b (based on LLaMA-7b). https://t.co/7ePEzWEtUB #ChatGPT #lmflow

1

47

11

9

14K

OptimalScale @OptimalScale

over 3 years ago

Hey everyone, happy weekend!😆 Our toolbox for finetuning large machine learning models LMFlow has some amazing updates that we wanna share with you!😉#AIGC #chatgptprompts #ArtificialIntelligence #LMFlow You can download all the models here: [https://t.co/vQG0eIsa2H]

1

4

1

362

Top Tweets for #LMFlow

Last Seen Hashtags on Sotwe

Trends for you

Most Popular Users