General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
1.2M Pulls 111 Tags Updated 2 years ago
🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.
15M Pulls 98 Tags Updated 2 years ago
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
1.3M Pulls 49 Tags Updated 2 years ago
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
522.6K Pulls 17 Tags Updated 2 years ago
A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
1M Pulls 5 Tags Updated 1 year ago
is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding.
148 Pulls 1 Tag Updated 1 year ago
ollama run wizard-vicuna-uncensored
1 Pull 1 Tag Updated 6 days ago
This is a Vietnamese language model capable of mastering Vietnamese and understanding Vietnamese. It can serve as a content writer, advertising copywriter, giving ideas, answer based on source,...
95 Pulls 1 Tag Updated 1 year ago
87 Pulls 5 Tags Updated 2 years ago
Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
350 Pulls 1 Tag Updated 2 years ago
Vidwan is a customized AI model based on LLaMA 3, designed to provide academic and research-based responses. It specializes in assisting with complex topics, answering in-depth questions, and providing structured insights.
81 Pulls 1 Tag Updated 1 year ago
Ultra-compact 256M vision-language model for video/image understanding. Supports visual QA, captioning, OCR, video analysis. Only 1.38GB VRAM. Built on SigLIP + SmolLM2. Available in Q8 and FP16. Apache 2.0 license.
1,472 Pulls 2 Tags Updated 7 months ago
Lightweight 2.2B vision model for GUI automation - clicks, types, scrolls on screenshots. Fine-tuned for agentic reasoning with normalized [0,1] coordinate output. Available in Q4_K_M, Q8_0, and FP16 quantizations. Apache 2.0 license.
560 Pulls 3 Tags Updated 7 months ago
7,942 Pulls 5 Tags Updated 1 year ago
Verified configuration + measured results for abliterated (uncensored) Qwen3.8-27B running as an autonomous redteam/sysadmin agent, served via llama-swap. This card documents OUR tested configuration and results on live tasks
282 Pulls 1 Tag Updated 2 days ago
Compact 500M vision-language model for video/image understanding. Supports visual QA, captioning, OCR, video analysis. Only 1.8GB VRAM. Built on SigLIP + SmolLM2. Available in Q8 and FP16. Apache 2.0 license.
1,081 Pulls 3 Tags Updated 8 months ago
The QwQ-LCoT-Instruct is a fine-tuned language model designed for advanced reasoning and instruction-following tasks. It leverages the Qwen2.5 base model and has been fine-tuned on the amphora/QwQ-LongCoT-130K dataset, focusing on chain-of-thought (
198 Pulls 2 Tags Updated 1 year ago
Holo-3.1 vision-language computer-use agents by H Company. Locate UI elements and drive web, desktop & mobile automation from a screenshot — returns clicks in normalized [0,1000] coords. 0.8B & 4B, instruct & thinking variants, Q4_K_M/Q8_0. Apache 2.0.
1,195 Pulls 7 Tags Updated 3 months ago
This is an AI model based on the Gemma4 Model Family, but designed to address issues such as sycophancy or unnecessary praise that may arise in AI models. (It has the ability to reason.) This has no connection to the OpenAssistans project.
97 Pulls 6 Tags Updated 2 months ago
25 Pulls 6 Tags Updated 2 months ago