DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
90.6M Pulls 35 Tags Updated 1 year ago
State-of-the-art coding AI trained on 2T tokens with project-level understanding and no content restrictions for unrestricted code generation.
909 Pulls 1 Tag Updated 8 months ago
This is the Q4_K converted version of the original Qiskit/mistral-small-3.2-24b-qiskit provided by IBM's Qiskit Huggingface. Please refer to the original mistral-small-3.2-24b-qiskit model card for more details.
21 Pulls 1 Tag Updated 1 month ago
This is a uncensored mistral 7b model (cas/nous-hermes-2-mistral-7b-dpo) with DAN as its system prompt. I originally intended to use DeepSeek for this, so the model thinks its name is deepseek.
889 Pulls 1 Tag Updated 1 year ago