metadata

language: en
tags:
  - coffeechat-ai
  - text-generation
  - side project
license: apache-2.0
datasets:
  - openwebtext
model-index:
  - name: coffeechat-ai
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          type: wikitext
          name: WikiText-103
        metrics:
          - type: Coffeechat AI
            name: CoffeeChat AI
            value: 21.1
co2_eq_emissions: 149200

CoffeeChat AI ☕

CoffeeChat AI is a lightweight, fine-tuned English language model based model.
It was Developed and customized by Adrian Charles and his team Bluckhut as a side project, with the goal of making an accessible, branded chatbot-style AI for text generation.

CoffeeChat AI can be used to generate text for creative, academic, or entertainment purposes.

Model Details

Developed by: Adrian Charles Obonyo
Base model: CoffeeChat AI
Model type: Transformer-based Language Model
Language: English
License: Apache 2.0
Model Description:
CoffeeChat AI, which has 82 million parameters, trained using knowledge distillation from vast datasets.
This version has been rebranded, documented, and prepared as part of a side project, with the intent of making AI more approachable.

Uses, Limitations, and Risks

Potential Uses

Writing assistance (grammar, autocompletion, brainstorming)
Creative writing and art (stories, poetry, dialogue generation)
Entertainment (chatbots, games, roleplay scenarios)
Educational projects (exploring NLP, transformers, model compression)

Limitations

CoffeeChat AI inherits the same limitations and biases like any other AI.
It may generate inaccurate, offensive, or biased outputs. It should not be relied on for factual correctness or sensitive applications.

How to Get Started with the Model

You can load and use CoffeeChat AI directly with Hugging Face transformers:

from transformers import pipeline, set_seed

generator = pipeline("text-generation", model="coffeechat-ai")
set_seed(42)

print(generator("Hello, I am CoffeeChat AI,", max_length=30, num_return_sequences=2))