HUB
Sign inSign up
mdelapenya

Manuel de la Peña

Community User

Docker, Inc

Spain

Displaying 1 to 30 of 52 repositories

image

Implements the Ralph-Loop pattern in code reviews

5m2.9K
image

moondream2 is a small vision language model designed to run efficiently on edge devices

1y2.0K
image

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens

2y2.7K
image

Qwen2 is a new series of large language models from Alibaba group

2y2.6K
image

Llama 3.2 of Meta goes small with 1B and 3B models.

2y3.6K
image

Embedding models on very large sentence level datasets

2y1.9K
image

Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B

2y1.7K
image

BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Ling

2y2.0K
image

LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna

2y700
image

CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks

2y787
image

A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger

2y790
image

StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes:

2y754
image

A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset

2y2.0K
image

A suite of text embedding models by Snowflake, optimized for performance

2y723
image

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes

2y904
image

A SOTA fact-checking model developed by Bespoke Labs

2y632
image

The 7B model released by Mistral AI, updated to version 0.3

2y814
image

A new small LLaVA model fine-tuned from Phi 3 Mini

2y776
image

A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function ca

2y586
image

Qwen2.5 models are pretrained on Alibaba latest large-scale dataset, encompassing up to 18 trillion

2y1.0K1
image

The latest series of Code-Specific Qwen models, with significant improvements in code generation, co

2y1.3K
image

A high-performing open embedding model with a large token context window

2y1.2K
image

Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsof

2y996
image

A series of models that convert HTML content to Markdown content, which is useful for content conver

2y801