Shivam-Uva/Plantinum-Chatbot

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Apr 2, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Shivam-Uva/Plantinum-Chatbot is an 8 billion parameter Llama 3.1 instruction-tuned causal language model developed by Shivam-Uva. Finetuned from unsloth/meta-llama-3.1-8b-instruct-bnb-4bit, this model was trained using Unsloth and Huggingface's TRL library for accelerated performance. It is designed for conversational AI tasks, leveraging its Llama 3.1 base for general-purpose chat applications.

Loading preview...

Shivam-Uva/Plantinum-Chatbot Overview

This model, developed by Shivam-Uva, is an 8 billion parameter instruction-tuned Llama 3.1 variant. It was finetuned from the unsloth/meta-llama-3.1-8b-instruct-bnb-4bit base model, indicating its foundation in Meta's Llama 3.1 architecture. A key aspect of its development is the use of Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Capabilities

  • Llama 3.1 Foundation: Inherits the strong general language understanding and generation capabilities of the Llama 3.1 instruction-tuned series.
  • Instruction Following: Optimized for responding to user instructions and engaging in conversational exchanges.
  • Efficient Training: Benefits from Unsloth's accelerated training techniques, suggesting potential for efficient deployment or further fine-tuning.

Good For

  • General Chatbot Applications: Suitable for building conversational agents that can understand and generate human-like text.
  • Instruction-Based Tasks: Effective for tasks requiring the model to follow specific commands or answer questions based on provided instructions.
  • Resource-Efficient Deployment: As an 8B parameter model, it offers a balance between performance and computational requirements, especially given its 4-bit quantization base.