Notes on Applicability of GPT-4 to Document Understanding
Paper
•
2405.18433
•
Published
Spaces-explorers
AI & ML interests
Contributors who are invited to beta-test our next big feature! Contact us if you want to join this team :-)
Recent Activity
View all activity
spaces-explorers's activity
Borchmann
authored
4
papers
2 months ago
Can Models Help Us Create Better Models? Evaluating LLMs as Data Scientists
Paper
•
2410.23331
•
Published
•
7
STable: Table Generation Framework for Encoder-Decoder Models
Paper
•
2206.04045
•
Published
Arctic-TILT. Business Document Understanding at Sub-Billion Scale
Paper
•
2408.04632
•
Published
kobiso
authored
a
paper
3 months ago
mariagrandury
authored
a
paper
3 months ago
raedle
authored
a
paper
5 months ago
mariagrandury
authored
a
paper
5 months ago
kobiso
authored
a
paper
6 months ago
mariagrandury
authored
a
paper
6 months ago
tolgacangoz
posted
an
update
8 months ago
Post
1125
Hi
@TimothyAlexisVass
, thanks for [this great blog post](https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space#the-4-channels-of-the-sdxl-latents)! Shouldn't this be like that?
https://github.com/TimothyAlexisVass/hf-colorspace-blogpost/pull/1
https://github.com/TimothyAlexisVass/hf-colorspace-blogpost/pull/1
Post
1630
Finally, I can post! 🚀
I created a Capybara-inspired Italian dataset by translating the initial instruction and running it through a pipeline to generate conversations. I used Claude Sonnet for translation and instruction generation, and Opus for generating the answers.
I hope this dataset proves useful for people working on 🇮🇹 language models.
⛁ Open sourcing the dataset here: efederici/capybara-claude-15k-ita
I created a Capybara-inspired Italian dataset by translating the initial instruction and running it through a pipeline to generate conversations. I used Claude Sonnet for translation and instruction generation, and Opus for generating the answers.
I hope this dataset proves useful for people working on 🇮🇹 language models.
⛁ Open sourcing the dataset here: efederici/capybara-claude-15k-ita
- 1 reply
Post
3869
I just shared a blogpost on https://nateraw.com explaining the motivation + process of training
nateraw/musicgen-songstarter-v0.2 - including training details, WandB logs, hparams, and notes on previous experiments.
Check it out here ⤵️
https://nateraw.com/posts/training_musicgen_songstarter.html
:) still kinda a WIP so if there's anything else you want to see, let me know.
Check it out here ⤵️
https://nateraw.com/posts/training_musicgen_songstarter.html
:) still kinda a WIP so if there's anything else you want to see, let me know.
- 3 replies
Post
4318
Turns out if you do a cute little hack, you can make
nateraw/musicgen-songstarter-v0.2 work on vocal inputs. 👀
Now, you can hum an idea for a song and get a music sample generated with AI 🔥🔥
Give it a try: ➡️ nateraw/singing-songstarter ⬅️
It'll take your voice and try to autotune it (because let's be real, you're no michael jackson), then pass it along to the model to condition on the melody. It works surprisingly well!
Now, you can hum an idea for a song and get a music sample generated with AI 🔥🔥
Give it a try: ➡️ nateraw/singing-songstarter ⬅️
It'll take your voice and try to autotune it (because let's be real, you're no michael jackson), then pass it along to the model to condition on the melody. It works surprisingly well!
manandey
authored
a
paper
9 months ago
manandey
authored
a
paper
10 months ago
Post
ICYMI! Nomic Embed v1.5: Resizable Production Embeddings with Matryoshka Representation Learning
- Variable embedding dimension from 64 <-> 768
- Outperforms text-embedding-ada-002 while achieving a 3x memory reduction
- Day 1 integrations with Langchain, LlamaIndex, MongoDB, and Sentence Transformers
Check out
nomic-ai/nomic-embed-text-v1.5 for the model weights.
Technical report: https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf
Blog Post: https://blog.nomic.ai/posts/nomic-embed-matryoshka
Original Tweet Thread: https://x.com/nomic_ai/status/1757782157374734665?s=20
- Variable embedding dimension from 64 <-> 768
- Outperforms text-embedding-ada-002 while achieving a 3x memory reduction
- Day 1 integrations with Langchain, LlamaIndex, MongoDB, and Sentence Transformers
Check out
nomic-ai/nomic-embed-text-v1.5 for the model weights.
Technical report: https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf
Blog Post: https://blog.nomic.ai/posts/nomic-embed-matryoshka
Original Tweet Thread: https://x.com/nomic_ai/status/1757782157374734665?s=20
nav13n
authored
a
paper
11 months ago
zpn
authored
a
paper
11 months ago
Post
ICYMI! Nomic Embed, the first fully open long context text embedder to beat OpenAI
- Open source, open weights, open data
- Beats OpenAI text-embeding-3-small and Ada on short and long context benchmarks
- Day 1 integrations with Langchain, LlamaIndex, MongoDB, and Sentence Transformers
Check out nomic-ai/nomic-embed-text-v1 for the model weights.
Technical report: https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf
Blog Post: https://blog.nomic.ai/posts/nomic-embed-text-v1
Original Tweet Thread: https://x.com/nomic_ai/status/1753082063048040829?s=20
- Open source, open weights, open data
- Beats OpenAI text-embeding-3-small and Ada on short and long context benchmarks
- Day 1 integrations with Langchain, LlamaIndex, MongoDB, and Sentence Transformers
Check out nomic-ai/nomic-embed-text-v1 for the model weights.
Technical report: https://static.nomic.ai/reports/2024_Nomic_Embed_Text_Technical_Report.pdf
Blog Post: https://blog.nomic.ai/posts/nomic-embed-text-v1
Original Tweet Thread: https://x.com/nomic_ai/status/1753082063048040829?s=20
- 1 reply