DeepCoder is a fully open-Source 14B coder model at O3-mini level, with a 1.5B version also available.
886.7K Pulls 9 Tags Updated 1 year ago
XBai o4 is a fourth-generation open-source language model that outperforms OpenAI-o3-mini in complex reasoning tasks.
46 Pulls 1 Tag Updated 11 months ago
Qwen2.5 0.5B fine-tuned on data distilled from GPT 4.1-Nano, 4o, o3, and o4-mini
599 Pulls 1 Tag Updated 1 year ago
4 Pulls 1 Tag Updated 11 months ago
LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities
555 Pulls 1 Tag Updated 9 months ago
382 Pulls 1 Tag Updated 11 months ago
LLaMA 3.1 8B Instruct model fine-tuned for advanced Wazuh security log analysis with instruction-following capabilities.
80 Pulls 1 Tag Updated 9 months ago
A quick and dirty ollama model made from https://huggingface.co/lmstudio-community/Phi-3.5-mini-instruct-GGUF
383 Pulls 1 Tag Updated 1 year ago
Lightweight, state-of-the-art model for Socratic interactions (fine tuned from Phi-3-mini-4k).
331 Pulls 15 Tags Updated 1 year ago
MiniCPM-V surpasses proprietary models such as GPT-4V, Gemini Pro, Qwen-VL and Claude 3 in overall performance, and support multimodal conversation for over 30 languages.
45.8K Pulls 8 Tags Updated 2 years ago
openbmb/MiniCPM-Llama3-V-2_5
2,578 Pulls 2 Tags Updated 1 year ago
A memory-efficient model configuration of Qwen3.6-35B-A3B using an upstream imatrix-calibrated IQ4_XS quantization and q4_0 KV cache. Designed for 24 GB VRAM
711 Pulls 1 Tag Updated 1 month ago
Stheno-v3.2-Zeta I have done a test run with multiple variations of the models, merged back to its base at various weights, different training runs too, and this Sixth iteration is the one I like most.
1,154 Pulls 1 Tag Updated 1 year ago
A fine-tuned Gemma 3 270M instruct model specialized in generating short, descriptive titles from the first message of a conversation.
18 Pulls 1 Tag Updated 1 month ago
The **Llama-3.1-8B-Instruct-STO-Master** is a high-performance fine-tune of Meta's Llama-3.1-8B-Instruct. This model represents the "Master Version" (Model E) of an extensive research project aimed at pushing the boundaries of 8B parameter architectures.
171 Pulls 1 Tag Updated 5 months ago
Qwen-SEA-LION-v4-32B-IT is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.
268 Pulls 3 Tags Updated 8 months ago
It is an LLM fine-tuned from Llama-3.2-3B-Instruct, capable of reasoning in the format <reasoning>...</reasoning><answer>...</answer>. Its capability might improve with further training.
67 Pulls 1 Tag Updated 1 year ago