Hugging Face 1Bit LLMs

HF1BitLLM's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts

Abhaykoul 

posted an update 5 days ago

view post

Post

1469

🔥 BIG ANNOUNCEMENT: THE HELPINGAI API IS LIVE! 🔥

Yo, the moment you’ve all been waiting for is here! 🚀 The HelpingAI API is now LIVE and ready to level up your projects! 🔥 We’re bringing that next-level AI goodness straight to your fingertips. 💯

No more waiting— it’s time to build something epic! 🙌

From now on, you can integrate our cutting-edge AI models into your own applications, workflows, and everything in between. Whether you’re a developer, a creator, or just someone looking to make some serious moves, this is your chance to unlock the full potential of emotional intelligence and adaptive AI.

Check out the docs 🔥 and let’s get to work! 🚀

👉 Check out the docs and start building (https://helpingai.co/docs)
👉 Visit the HelpingAI website (https://helpingai.co/)

See translation

• 
• 
• 
• 6 replies

·

🔥

2

2

🚀

2

2

+

Reply

erikkaum 

posted an update about 1 month ago

view post

Post

1703

A while ago I started experimenting with compiling the Python interpreter to WASM.

To build a secure, fast, and lightweight sandbox for code execution — ideal for running LLM-generated Python code.

- Send code simply as a POST request
- 1-2ms startup times

Hack away:
https://github.com/ErikKaum/runner

🔥

8

8

👀

6

6

+

Reply

medmekk 

in HF1BitLLM/README about 2 months ago

Running Llama3-8B-1.58-100B-tokens on CPU

3

#2 opened 2 months ago by

chiauho

chiauho 

in HF1BitLLM/README about 2 months ago

Running Llama3-8B-1.58-100B-tokens on CPU

3

#2 opened 2 months ago by

chiauho

chiauho 

in HF1BitLLM/Llama3-8B-1.58-100B-tokens about 2 months ago

Triton error while running demo code

2

#11 opened 2 months ago by

chiauho

medmekk 

in HF1BitLLM/Llama3-8B-1.58-100B-tokens about 2 months ago

Triton error while running demo code

2

#11 opened 2 months ago by

chiauho

1024m 

authored 4 papers 2 months ago

RKadiyala at SemEval-2024 Task 8: Black-Box Word-Level Text Boundary Detection in Partially Machine Generated Texts

Paper • 2410.16659 • Published Oct 22

Large Language Models for Cross-lingual Emotion Detection

Paper • 2410.15974 • Published Oct 21 • 1

1024m at SMM4H 2024: Tasks 3, 5 & 6 -- Ensembles of Transformers and Large Language Models for Medical Text Classification

Paper • 2410.15998 • Published Oct 21 • 1

Augmenting Legal Decision Support Systems with LLM-based NLI for Analyzing Social Media Evidence

Paper • 2410.15990 • Published Oct 21 • 1

medmekk 

updated a model 3 months ago

HF1BitLLM/Llama3-8B-1.58-100B-tokens

Text Generation • Updated Sep 19 • 3.76k • 165

medmekk 

updated a Space 3 months ago

Sleeping

📈

README

medmekk 

updated 2 models 3 months ago

HF1BitLLM/Llama3-8B-1.58-Sigmoid-k100-10B-tokens

Text Generation • Updated Sep 18 • 20 • 11

HF1BitLLM/Llama3-8B-1.58-Linear-10B-tokens

Text Generation • Updated Sep 18 • 431 • 9

sugatoray 

posted an update 4 months ago

view post

Post

549

Open-Devin has been rebranded as OpenHands on GitHub.

Docs: https://docs.all-hands.dev/modules/usage/llms/local-llms
GitHub: https://github.com/All-Hands-AI/OpenHands
Paper: https://arxiv.org/abs/2407.16741
Post on X: https://x.com/gneubig/status/1828097484599759349?s=61&t=KYwlyP7fHVw9cFnwZFzIag

• 

• 
• 1 reply

·

👀

2

2

+

Reply

Abhaykoul 

posted an update 4 months ago

view post

Post

2905

Introducing HelpingAI2-9B, an emotionally intelligent LLM.
Model Link : https://huggingface.co/OEvortex/HelpingAI2-9B
Demo Link: Abhaykoul/HelpingAI2

This model is part of the innovative HelpingAI series and it stands out for its ability to engage users with emotional understanding.

Key Features:
-----------------

* It gets 95.89 score on EQ Bench greather than all top notch LLMs, reflecting advanced emotional recognition.
* It gives responses in empathetic and supportive manner.

Must try our demo: Abhaykoul/HelpingAI2

• 
• 1 reply

·

🔥

8

8

❤️

3

3

👀

1

1

+

Reply

dongwonjo 

authored a paper 6 months ago

Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models

Paper • 2406.12311 • Published Jun 18 • 6

Abhaykoul 

posted an update 7 months ago

view post

Post

2701

# HelpingAI 9B: Cutting Edge Emotionally Intelligent AI

If you have ever felt that AI not understand your emotions or you not get human like fell while taking to him than this blog is for you!
In this BlogPost we will be exploring [HelpingAI 9B](https://huggingface.co/spaces/Abhaykoul/HelpingAI-9B) is an Highly Emotionally Intelligent AI which beated all top notch ai like GPT4o, GPT4, Claude3 Opus on EQ-Bench.

## What is HelpingAI 9B?
HelpingAI-9B is the fine-tuned Llama2 model crafted for emotionally intelligent conversations. This model excels in empathetic engagement, offering understanding and support through dialogue spanning various topics and situations. Its goal is to serve as a supportive AI companion, adept at resonating with users' emotions and communication requirements.

## Method
We gathered a large volume of high-quality human chat data, which was then filtered and refined to create three types of datasets:
1. DPO - Initially, we trained the AI on a substantial DPO dataset to grasp human conversation patterns, enabling it to discern which types of output to generate and which to avoid.
2. Alpaca - Subsequently, we trained it on an Alpaca-type dataset to enhance its human-like responses.
3. SFT - Finally, once the AI fully comprehended human interactions, we trained it on an SFT dataset to broaden its knowledge base.

## Evaluation


## Conclusion:
HelpingAI is a large step toward understanding human emoions and give response like them. It can help us lot in making AI better for NLP.
Thanks!

Model Link: - https://huggingface.co/OEvortex/HelpingAI-9B

Demo link: - https://huggingface.co/spaces/Abhaykoul/HelpingAI-9B

• 

• 
• 
• 
• 9 replies

·

🔥

6

6

🤗

1

1

+

Reply

Abhaykoul 

posted an update 8 months ago

view post

Post

2817

Introduction to HelpingAI-3B-v2.1 and HelpingAI-3B-v2.2

These models are designed to engage in dialogues that are not only contextually relevant but also deeply empathetic, tailoring their responses to the emotional state and context of the user. With advanced emotional understanding capabilities, they can comfort, celebrate, and address complex feelings with a level of emotional nuance that is unparalleled in the AI domain.

Emotional Intelligence Capabilities

The core of these models lies in their emotional intelligence capabilities. They exhibit several key traits that enable them to respond emotionally resonant:

- Emotion recognition and validation: The models can identify and validate the emotions expressed by the user, ensuring that their responses are grounded in understanding.
- Empathetic perspective-taking: They are capable of taking the user's perspective, understanding their feelings, and responding with empathy.
- Generating emotionally supportive language: The models can generate language that is supportive and comforting, tailored to the user's emotional state.
- Contextual emotional attunement: They can adapt their communication style to match the emotional context of the conversation, ensuring relevance and appropriateness.
- Using appropriate tone, word choice, and emotional expression**: The models are adept at using the right tone, words, and emotional expressions to convey their messages effectively.

Examples of Emotionally Intelligent Responses

Let's take a look at how these models can adapt their communication style with emotional nuance:

- Comforting someone grieving: The models can offer empathetic responses, acknowledging the user's feelings and suggesting practical ways to cope with grief.
- Celebrating positive news: They can generate responses that are joyful and supportive, encouraging the user to enjoy their positive experiences.
OEvortex/HelpingAI-3B-v2.1
OEvortex/HelpingAI-3B-v2.2

🔥

2

2

🚀

1

1

👀

1

1

+

Reply