Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

Phocinae-Largha-150M-v1

Phocinae-Largha-150M-v1 is a compact, bilingual decision model hosted on GitHub, weighing in at 144.3M parameters. Designed for efficiency, this model aims to facilitate significant decisions despite its small footprint. It provides a foundational resource for developers and researchers working with bilingual data and decision-making processes, emphasizing impactful outcomes from a lightweight architecture.

View Repository
Share
View Repository
Share

Phocinae-Largha-150M-v1, also known as 斑海豹 (Spotted Seal), is an open-source project available on GitHub that introduces a 144.3 million parameter bilingual decision model. This model is specifically engineered to be tiny yet capable of handling big decisions, offering a balance between computational efficiency and decision-making power. Its bilingual nature suggests applicability in environments requiring processing and decision support across two languages, making it a versatile tool for various applications.

Read More

The repository provides a comprehensive structure, including directories for evaluation results (`.eval_results`), GitHub workflows (`.github`), calibration data (`calib`), datasets, documentation (`docs`), figures, and development tools. Key files such as `BENCHMARKS.md`, `CITATION.cff`, `CODE_OF_CONDUCT.md`, `CONTRIBUTING.md`, `LICENSE`, `MODEL_CARD.md`, `NOTICE`, `README.md`, `README.zh.md`, `SECURITY.md`, and `SHA256SUMS` are included, offering insights into the model's performance, licensing, contribution guidelines, and security practices.

The project emphasizes transparency and reproducibility, with detailed commit messages indicating updates to benchmarks, documentation, and dataset synchronization. The `NOTICE` file specifically mentions third-party attributions, including `mmBERT-small MIT` and `typed-decisions A`, highlighting the collaborative and open-source spirit of the project. The presence of both English and Chinese README files (`README.md` and `README.zh.md`) further underscores its bilingual focus and accessibility to a broader audience.

Phocinae-Largha-150M-v1 is ideal for researchers and developers looking for a compact, high-impact decision model that can operate efficiently with bilingual inputs. Its open-source nature encourages community contributions and further development, making it a valuable resource for advancing AI applications in multilingual contexts. The project's commitment to detailed documentation and clear licensing ensures that users can easily integrate and build upon this foundational model.

  • CategoryAI Models & LLMs
  • Pricing ModelOpen source
  • DeploymentCloud
  • PlatformsWeb

  • 144.3M parameter bilingual decision model

  • Compact and efficient model architecture

  • Supports decision-making processes

  • Includes evaluation results and benchmarks

  • Comprehensive documentation in English and Chinese

  • Open-source project with MIT license (for mmBERT-small)

  • Contribution guidelines available

  • Security policy outlined

  • Detailed model card provided

  • Third-party attributions listed

  • Dataset synchronization and management

  • Calibration data included

  • Tools for development and analysis

  • Version control with commit history

  • Repository files navigation

  1. Clone the repository: Use `git clone` to download the Phocinae-Largha-150M-v1 project to your local machine.

  2. Review documentation: Read `README.md` and `README.zh.md` for an overview, and `MODEL_CARD.md` for model specifics.

  3. Install dependencies: Check `requirements.txt` for necessary libraries and install them using `pip install -r requirements.txt`.

  4. Explore datasets: Navigate the `datasets` directory to understand the training and evaluation data used.

  5. Run evaluations: Utilize scripts or instructions in `.eval_results` and `calib` to reproduce benchmarks or test the model.

  6. Contribute: Refer to `CONTRIBUTING.md` for guidelines on how to submit improvements or new features.

  • Bilingual Decision Support
  • Resource-Constrained AI
  • Multilingual NLP Research
  • Educational AI Projects
  • Custom Model Development

Phocinae-Largha-150M-v1 Reviews

Loading...

Popular AI Tools Like Phocinae-Largha-150M-v1

Ling

AI GitHub Repos

Ling is an open-source mixture-of-experts language model family from Ant Group's inclusionAI, released on GitHub under the MIT license. It ships in multiple sizes for general…

AI Models & LLMs
View Tool

AI GitHub Repos

Open-source mixture-of-experts language model family from Ant Group's inclusionAI, released on GitHub under the MIT license. It ships in multiple sizes for general…Ling is an open-source mixture-of-experts language model family from Ant Group's inclusionAI, released on GitHub under the MIT license. It ships in multiple sizes for general…

AI Models & LLMs
See the Top 250 AI GitHub Repos

AnyJev

AI GitHub Repos

AnyJev is a GitHub project that transforms any large language model (LLM) into a Jev-style decision model. It offers typed decisions and real probabilities without requiring…

AI Models & LLMs
View Tool

AI GitHub Repos

GitHub project that transforms any large language model (LLM) into a Jev-style decision model. It offers typed decisions and real probabilities without requiring…AnyJev is a GitHub project that transforms any large language model (LLM) into a Jev-style decision model. It offers typed decisions and real probabilities without requiring…

AI Models & LLMs
See the Top 250 AI GitHub Repos

Chinese-LLaMA-Alpaca

AI GitHub Repos

Chinese-LLaMA-Alpaca is a GitHub repository offering Chinese language models, LLaMA and Alpaca, with local CPU/GPU training and deployment capabilities. It supports researchers…

AI Models & LLMs
View Tool

AI GitHub Repos

GitHub repository offering Chinese language models, LLaMA and Alpaca, with local CPU/GPU training and deployment capabilities. It supports researchers…Chinese-LLaMA-Alpaca is a GitHub repository offering Chinese language models, LLaMA and Alpaca, with local CPU/GPU training and deployment capabilities. It supports researchers…

AI Models & LLMs
See the Top 250 AI GitHub Repos

llm-architecture-from-scratch is a GitHub repository by Yeonwoo Sung that focuses on implementing large language model architectures from scratch using PyTorch. It provides a…

AI Models & LLMs
View Tool

ChatGLM2-6B

AI GitHub Repos

ChatGLM2-6B is an open bilingual chat language model designed to facilitate seamless communication in multiple languages. It offers advanced language processing capabilities,…

AI Models & LLMs
View Tool

AI GitHub Repos

Open bilingual chat language model designed to facilitate seamless communication in multiple languages. It offers advanced language processing capabilities,…ChatGLM2-6B is an open bilingual chat language model designed to facilitate seamless communication in multiple languages. It offers advanced language processing capabilities,…

AI Models & LLMs
See the Top 250 AI GitHub Repos

Decider

AI GitHub Repos

Decider is a family of System One-style models fine-tuned from Qwen3.5. It is designed for making one-pass typed decisions with calibrated probabilities, providing a streamlined…

AI Models & LLMs
View Tool

AI GitHub Repos

Family of System One-style models fine-tuned from Qwen3.5. It is designed for making one-pass typed decisions with calibrated probabilities, providing a streamlined…Decider is a family of System One-style models fine-tuned from Qwen3.5. It is designed for making one-pass typed decisions with calibrated probabilities, providing a streamlined…

AI Models & LLMs
See the Top 250 AI GitHub Repos

rizzo-flow

AI GitHub Repos

Rizzo-flow is an open-source project that enables typed decisions from a large language model (LLM) without generating a single token. It provides a local alternative to Jev,…

Coding & Development
View Tool

AI GitHub Repos

Open-source project that enables typed decisions from a large language model (LLM) without generating a single token. It provides a local alternative to Jev,…Rizzo-flow is an open-source project that enables typed decisions from a large language model (LLM) without generating a single token. It provides a local alternative to Jev,…

Coding & Development
See the Top 250 AI GitHub Repos

Jeff

AI GitHub Repos

Jeff is an open-source model designed for making rapid decisions across various domains. It utilizes a 0.8 billion parameter 'System 1' model to provide calibrated probabilities…

AI Models & LLMs
View Tool

AI GitHub Repos

Open-source model designed for making rapid decisions across various domains. It utilizes a 0.8 billion parameter 'System 1' model to provide calibrated probabilities…Jeff is an open-source model designed for making rapid decisions across various domains. It utilizes a 0.8 billion parameter 'System 1' model to provide calibrated probabilities…

AI Models & LLMs
See the Top 250 AI GitHub Repos
1 of 8