Llamacha/monolingual-quechua-iic
Viewer
β’
Updated
β’
175k
β’
678
β’
4
David Quispe PRO
daqc
AI & ML interests
Education
Recent Activity
liked
a dataset
1 day ago
Llamacha/monolingual-quechua-iic
liked
a dataset
1 day ago
pollitoconpapass/cuzco-quechua-translation-spanish
liked
a dataset
1 day ago
Zeal-Nir/quechua-audioset-4GB
Organizations
daqc's activity
liked
7
datasets
1 day ago
pollitoconpapass/cuzco-quechua-translation-spanish
Viewer
β’
Updated
β’
135k
β’
42
β’
1
Zeal-Nir/quechua-audioset-4GB
Viewer
β’
Updated
β’
220
β’
32
β’
1
pollitoconpapass/quechua-cuzco-bible-audio-dataset
Viewer
β’
Updated
β’
159
β’
41
β’
1
pollitoconpapass/new-cuzco-quechua-translation-dataset
Viewer
β’
Updated
β’
17.3k
β’
20
β’
1
cportoca/CS224S_Quechua_Project_emotion_dataset
Viewer
β’
Updated
β’
12.4k
β’
47
β’
1
cportoca/CS224S_Quechua_Project
Viewer
β’
Updated
β’
823
β’
71
β’
2
upvoted
a
paper
1 day ago
liked
a
dataset
1 day ago
liked
a
model
1 day ago
upvoted
a
collection
1 day ago
reacted to
prithivMLmods's
post with π€
1 day ago
Post
2721
Triangulum Catalogued π₯π«
π―Triangulum is a collection of pretrained and instruction-tuned generative models, designed for multilingual applications. These models are trained using synthetic datasets based on long chains of thought, enabling them to perform complex reasoning tasks effectively.
+ Triangulum-10B : prithivMLmods/Triangulum-10B
+ Quants : prithivMLmods/Triangulum-10B-GGUF
+ Triangulum-5B : prithivMLmods/Triangulum-5B
+ Quants : prithivMLmods/Triangulum-5B-GGUF
+ Triangulum-1B : prithivMLmods/Triangulum-1B
+ Quants : prithivMLmods/Triangulum-1B-GGUF
π―Triangulum is a collection of pretrained and instruction-tuned generative models, designed for multilingual applications. These models are trained using synthetic datasets based on long chains of thought, enabling them to perform complex reasoning tasks effectively.
+ Triangulum-10B : prithivMLmods/Triangulum-10B
+ Quants : prithivMLmods/Triangulum-10B-GGUF
+ Triangulum-5B : prithivMLmods/Triangulum-5B
+ Quants : prithivMLmods/Triangulum-5B-GGUF
+ Triangulum-1B : prithivMLmods/Triangulum-1B
+ Quants : prithivMLmods/Triangulum-1B-GGUF
- 1 reply
reacted to
roseking's
post with π
1 day ago
Post
2353
π€ Hugging Face Download Tool
The Hugging Face Download Tool is a sophisticated graphical user interface application designed to simplify the process of downloading resources from Hugging Face repositories. This tool addresses common challenges in model and file downloads through its intelligent features and user-friendly interface.
β¨ Key Features
- π₯οΈ Intuitive graphical interface for easy operation
- π Advanced retry mechanism with smart error handling
- βΈοΈ Resume capability for interrupted downloads
- π Real-time download status monitoring
- π Secure access to private repositories via token authentication
π οΈ Technical Highlights
The tool implements several advanced features to ensure reliable downloads:
- π¦ Chunk-based downloading with 1MB segments
- β‘ Adaptive retry intervals (5-300 seconds) based on error types
- π Connection pooling for optimized performance
- π‘οΈ Built-in rate limiting protection
- π Secure token handling for private repository access
This tool is ideal for researchers, developers, and AI practitioners who regularly work with Hugging Face resources and need a reliable, user-friendly download solution. π» It supports all major operating systems and requires minimal setup, making it accessible to users of all technical levels. π
GitHubοΌhttps://github.com/2404589803/hf_downloader
The Hugging Face Download Tool is a sophisticated graphical user interface application designed to simplify the process of downloading resources from Hugging Face repositories. This tool addresses common challenges in model and file downloads through its intelligent features and user-friendly interface.
β¨ Key Features
- π₯οΈ Intuitive graphical interface for easy operation
- π Advanced retry mechanism with smart error handling
- βΈοΈ Resume capability for interrupted downloads
- π Real-time download status monitoring
- π Secure access to private repositories via token authentication
π οΈ Technical Highlights
The tool implements several advanced features to ensure reliable downloads:
- π¦ Chunk-based downloading with 1MB segments
- β‘ Adaptive retry intervals (5-300 seconds) based on error types
- π Connection pooling for optimized performance
- π‘οΈ Built-in rate limiting protection
- π Secure token handling for private repository access
This tool is ideal for researchers, developers, and AI practitioners who regularly work with Hugging Face resources and need a reliable, user-friendly download solution. π» It supports all major operating systems and requires minimal setup, making it accessible to users of all technical levels. π
GitHubοΌhttps://github.com/2404589803/hf_downloader
-
- 2 replies
updated
a
model
3 days ago
liked
2
Spaces
3 days ago
updated
2
datasets
4 days ago
updated
a
model
4 days ago
reacted to
lewtun's
post with π
4 days ago
Post
6624
We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute π₯
How? By combining step-wise reward models with tree search algorithms :)
We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"
We're open sourcing the full recipe and sharing a detailed blog post.
In our blog post we cover:
π Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.
π Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.
π§ Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM
Here's the links:
- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute
- Code: https://github.com/huggingface/search-and-learn
Enjoy!
How? By combining step-wise reward models with tree search algorithms :)
We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"
We're open sourcing the full recipe and sharing a detailed blog post.
In our blog post we cover:
π Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.
π Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.
π§ Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM
Here's the links:
- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute
- Code: https://github.com/huggingface/search-and-learn
Enjoy!
- 2 replies