1 2 3

dan su

sudanenator

AI & ML interests

None yet

Recent Activity

reacted to danielhanchen's post with 🔥 4 days ago

Deepseek V3, including GGUF + bf16 versions are now uploaded! Includes 2, 3, 4, 5, 6 and 8-bit quantized versions. GGUFs: https://huggingface.co/unsloth/DeepSeek-V3-GGUF bf16: https://huggingface.co/unsloth/DeepSeek-V3-bf16 Min. hardware requirements to run: 48GB RAM + 250GB of disk space for 2-bit. See how to run them with examples and the full collection: https://huggingface.co/collections/unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c

reacted to reddgr's post with 👀 4 days ago

Major update on the Talking to Chatbots dataset! Expanded the 'wrapped' dataset (one row per chat) to 2.86k records, and the 'unwrapped' version (one row per conversation turn) to 11k records. The main source is my ChatGPT archive with nearly 2 years of chats. It is still a work in progress as I incorporate chats from other sources and qualitative metrics (SCBN) for responses. https://huggingface.co/datasets/reddgr/talking-to-chatbots-unwrapped-chats https://huggingface.co/datasets/reddgr/talking-to-chatbots-chats

View all activity

Organizations

sudanenator's activity

reacted to danielhanchen's post with 🔥 4 days ago

Post

2995

Deepseek V3, including GGUF + bf16 versions are now uploaded!

Includes 2, 3, 4, 5, 6 and 8-bit quantized versions.

GGUFs: unsloth/DeepSeek-V3-GGUF
bf16: unsloth/DeepSeek-V3-bf16

Min. hardware requirements to run: 48GB RAM + 250GB of disk space for 2-bit.

See how to run them with examples and the full collection: unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c

reacted to reddgr's post with 👀 4 days ago

Post

2254

Major update on the Talking to Chatbots dataset! Expanded the 'wrapped' dataset (one row per chat) to 2.86k records, and the 'unwrapped' version (one row per conversation turn) to 11k records. The main source is my ChatGPT archive with nearly 2 years of chats. It is still a work in progress as I incorporate chats from other sources and qualitative metrics (SCBN) for responses.

reddgr/talking-to-chatbots-unwrapped-chats

reddgr/talking-to-chatbots-chats

reacted to Xenova's post with 👍 6 months ago

Post

7981

Introducing Whisper Diarization: Multilingual speech recognition with word-level timestamps and speaker segmentation, running 100% locally in your browser thanks to 🤗 Transformers.js!

Tested on this iconic Letterman interview w/ Grace Hopper from 1983!
- Demo: Xenova/whisper-speaker-diarization
- Source code: Xenova/whisper-speaker-diarization

1 reply

upvoted an article 9 months ago

Article

How to Finetune phi-3 on MacBook Pro

•

Apr 24, 2024

• 65

reacted to chansung's post with ❤️ 9 months ago

Post

4402

💻 Smoothing the Transition from Service LLM to Local LLM

Imagine your go-to LLM service is down, or you need to use it offline – yikes! This project is all about having that "Plan B" ready to go. Here's LLaMA Duo I've been building with @sayakpaul :

✨ Fine-tune a smaller LLM: We used Hugging Face's alignment-handbook to teach a smaller-sized LLM to mimic my favorite large language model. Think of it as that super-smart AI assistant getting a capable understudy.

🤖 Batch Inference: Let's get that fine-tuned LLM working! My scripts generate lots of text like a champ, and we've made sure things run smoothly even with bigger workloads.

🧐 Evaluation: How well is my small LLM doing? We integrated with the Gemini API to use it as an expert judge – it compares my model's work to the original. Talk about a tough critic!

🪄 Synthetic Data Generation: Need to boost that model's performance? Using Gemini's feedback, we can create even more training data, custom-made to make the LLM better.

🧱 Building Blocks: This isn't just a one-time thing – it's a toolkit for all kinds of LLMOps work. Want to change your evaluation metrics? Bring in models trained differently? Absolutely, let's make it happen.

Why this project is awesome:

💪 Reliability: Keep things running no matter what happens to your main LLM source.
🔒 Privacy: Process sensitive information on your own terms.
🗺️ Offline capable: No internet connection? No problem!
🕰️ Version Control: Lock in your favorite LLM's behavior, even if the service model changes.

We'm excited to share the code on GitHub. Curious to see what you all think! 👉🏻 https://github.com/deep-diver/llamaduo