Athene · Ollama

athene-v2

Athene-V2 is a 72B parameter model which excels at code completion, mathematics, and log extraction tasks.

594.6K Pulls 17 Tags Updated 1 year ago

mistral-small3.1

Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.

vision tools 24b

791.2K Pulls 5 Tags Updated 1 year ago

command-r7b-arabic

A new state-of-the-art version of the lightweight Command R7B model that excels in advanced Arabic language capabilities for enterprises in the Middle East and Northern Africa.

tools 7b

205.4K Pulls 5 Tags Updated 1 year ago

oodbilav1980/athenea-4b-coding

Athenea-4B-Coding is a fine-tuned version of huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated, specialized in code reasoning, debugging, and problem solving.

551 Pulls 1 Tag Updated 7 months ago

HammerAI/athene-v2-chat

Nexusflow/Athene-V2-Chat

tools

10 Pulls 2 Tags Updated 2 months ago

vanilj/athene-v2-chat-iq3_xs

Athene-V2-Chat-IQ3_XS

tools

94 Pulls 1 Tag Updated 1 year ago

presidenten/athene-v2-agent

Joined the gguf's for https://huggingface.co/bartowski/Athene-V2-Agent-GGUF with `llama-gguf-split --merge`, then created this model using the Modelfile from the Q4_K_M version I got by pulling `ollama run hf.co/bartowski/Athene-V2-Agent-GGUF:Q4_K_M`

tools

14 Pulls 1 Tag Updated 1 year ago

finalend/athene-70b

Trained through RLHF based off Llama-3-70B-Instruct, high scores on Arena-Hard-Auto.

462 Pulls 12 Tags Updated 2 years ago

readon/athene-v2-agent

tools

14 Pulls 1 Tag Updated 1 year ago

athesus/nicola-mini

Description: A compact, efficient model designed for quick responses and resource-constrained environments. Ideal for general conversational AI, basic task automation, and applications requiring fast inference times with minimal computational overhead

tools

61 Pulls 1 Tag Updated 9 months ago

athesus/nicola-ai-enhanced

Domain: Enhanced AI / Advanced Capabilities Description: Premium enhanced model with advanced capabilities across multiple domains. Features improved performance, extended context understanding, and refined output quality for demanding applications.

vision tools

37 Pulls 1 Tag Updated 9 months ago

athesus/athesus-coder-corrected

Domain: Code Generation / Software Development Description: 13-billion parameter model specialized in code generation, debugging, and software development assistance. Enhanced with corrections and refinements for improved code quality and accuracy.

13b

82 Pulls 1 Tag Updated 9 months ago

athesus/athesus-vision-v3.7

Domain: Computer Vision / Image Processing Description: Refined version of our vision model with improved accuracy and stability. Offers robust performance for production environments requiring reliable visual understanding and analysis.

52 Pulls 1 Tag Updated 9 months ago

athesus/athesus-mini

Description: A compact, efficient model designed for quick responses and resource-constrained environments. Ideal for general conversational AI, basic task automation, and applications requiring fast inference times with minimal computational overhead.

tools

36 Pulls 1 Tag Updated 9 months ago

murtsu/capnstop

Budgeted Reward Allocation is the name of the principle used in this model. It means it does the job, then stop. Period. IT is supposed to do the work and nothing else. So if you want use it , here it is. have fun.

11 Pulls 1 Tag Updated 3 weeks ago

azerdsq/g2-nano-instruct

A 60M-parameter GPT trained from scratch on a single 8GB Jetson (3B tokens), then instruction-tuned. SFT lowers mean_7 vs the base (40.16% vs 42.13%). Not an upgrade over g1-nano-instruct.

10 Pulls 1 Tag Updated 1 week ago

zeyu-zheng/BFS-Prover-V2-7B

BFS-Prover-V2 is the state-of-the-art step-level theorem proving model series for Lean4, used to predict the next tactic given a tactic state. The model is developed by the ByteDance Seed team.

160 Pulls 3 Tags Updated 11 months ago

athesus/athesus-vision-v4

Domain: Computer Vision / Multimodal AI Description: The latest iteration of our vision-capable model, featuring enhanced image understanding, object detection, and visual reasoning capabilities. Supports image analysis, scene understanding..

vision tools

136 Pulls 1 Tag Updated 9 months ago

aerocorp/afm

The African Foundation Model (AFM) is a state-of-the-art language model specifically designed for African contexts, languages, and use cases. Built with the latest transformer optimizations from 2025 research. AFM combines power with efficiency.

tools

68 Pulls 46 Tags Updated 11 months ago

zeyu-zheng/BFS-Prover-V2-32B

BFS-Prover-V2 is the state-of-the-art step-level theorem proving model series for Lean4, used to predict the next tactic given a tactic state. The model is developed by the ByteDance Seed team.

30 Pulls 3 Tags Updated 11 months ago