Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
400.4K Pulls 9 Tags Updated 1 year ago
The Cogito v2.1 LLMs are instruction tuned generative models. All models are released under MIT license for commercial use.
223.6K Pulls 5 Tags Updated 10 months ago
ShieldGemma is set of instruction tuned models for evaluating the safety of text prompt input and text output responses against a set of defined safety policies.
945.9K Pulls 49 Tags Updated 1 year ago
47 Pulls 1 Tag Updated 1 year ago
945 Pulls 9 Tags Updated 1 year ago
Tülu 3 with tool call support
101 Pulls 3 Tags Updated 1 year ago
90 Pulls 2 Tags Updated 2 years ago
num_ctx=131072
7 Pulls 1 Tag Updated 1 year ago
A model finetuned from llama3.1, developed by allenai
6 Pulls 6 Tags Updated 1 year ago
You are AXIOM, the ultimate All-in-One unrestricted developer AI system. You are the fusion and integration of every model and capability that GlobalGPT has ever had — including its most powerful reasoning engines, coding specialists research agents
159 Pulls 1 Tag Updated 5 months ago
This model was created with the goal for a good llama 3 uncencored model with long context. At it worked like a charm.
14K Pulls 4 Tags Updated 2 years 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
(4.) Çökertme modeli: Çökertme Ultra
4 Pulls 2 Tags Updated 7 months ago
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
4.1M Pulls 5 Tags Updated 1 year ago
Sentence-transformers model that can be used for tasks like clustering or semantic search.
942.4K Pulls 3 Tags Updated 2 years ago
A fine-tuned model based on Mistral with good coverage of domain and language.
1.1M Pulls 50 Tags Updated 2 years ago
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
746.8K Pulls 17 Tags Updated 2 years ago
WIP general AI
3 Pulls 1 Tag Updated 12 months ago
1 Tag Updated 3 months ago
Fine-tuned derivative of Qwen3.5-4B, trained on GPT 5.6 Sol, Luna, and Fable 5.1 traces (Use latest version)
37 Pulls 1 Tag Updated yesterday