DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
485.7K Pulls 3 Tags Updated 7 months ago
The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
5.2M Pulls 36 Tags Updated 2 years ago
A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.
954.8K Pulls 33 Tags Updated 1 year ago
OLMo 2 is a new family of 7B and 13B models trained on up to 5T tokens. These models are on par with or better than equivalently sized fully open models, and competitive with open-weight models such as Llama 3.1 on English academic benchmarks.
3.7M Pulls 9 Tags Updated 1 year ago
1,597 Pulls 1 Tag Updated 2 years ago
pulled from https://huggingface.co/second-state/Octopus-v2-GGUF/blob/main/Octopus-v2-Q4_K_M.gguf
171 Pulls 1 Tag Updated 2 years ago
50 Pulls 1 Tag Updated 2 years ago
A coding assistant with a 32k context window.
29 Pulls 4 Tags Updated 2 years ago
1 Pull 1 Tag Updated 4 months ago
1 Tag Updated 3 months ago
OWASP Top 10 (2021) vulnerability detection model. Analyzes code for SQL injection, XSS, hardcoded secrets, authentication bypass, SSRF, and more. Just paste your code and get instant security analysis
7 Pulls 1 Tag Updated 6 days ago
Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
16.3K Pulls 4 Tags Updated 1 week ago
GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.
6M Pulls 3 Tags Updated 5 months ago
A balanced configuration variant of Qwen3.5-4B, planned for FIM (Fill-In-the-Middle) and Tool Calling in restrict capacity environments. Using the Q3_K_S GGUF quantization from HuggingFace (unsloth).
147 Pulls 2 Tags Updated 2 weeks ago
Laguna XS.2 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
20.3K Pulls 7 Tags Updated 2 months ago
Omini-pyauto-1.5b is a fine-tuned Python automation code generation model built on top of Qwen2.5-Coder-1.5B-Instruct. It specializes in generating production-ready automation scripts for three major frameworks: Playwright, SeleniumBase, and Selenium.
140 Pulls 1 Tag Updated 3 months ago
tools support and a 128k context length by default
1,302 Pulls 1 Tag Updated 9 months ago
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
3.8M Pulls 5 Tags Updated 1 year ago
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
660.8K Pulls 17 Tags Updated 2 years ago
The long-context version of Qwen2.5, supporting 1M-token context lengths
3,480 Pulls 2 Tags Updated 1 year ago