Hugging Face's logo

DeepMount00
/
Phi-3-Large-5.6b

Text Generation
Transformers
Safetensors
Italian
English
llama
conversational
Inference Endpoints
text-generation-inference
Model card Files Community
Phi-3-Large-5.6b / README.md
DeepMount00's picture
DeepMount00
Update README.md
f09b6bb verified
preview code
|
raw history blame contribute delete
No virus
1.23 kB
metadata
language:
  - it
  - en
license: apache-2.0
pipeline_tag: text-generation

Phi-3-mini-4k-instruct 5.6b

Model Details

  • Name: Expanded microsoft/Phi-3-mini-4k-instruct (Large Experiment)
  • Version: 1.0
  • Release Date: 06/05/2024
  • Model Type: Instruction-based Large Language Model
  • Developer: Montebovi Michele

Intended Use

  • Primary Use Case: This model is an experimental expansion of the microsoft/Phi-3-mini-4k-instruct instruct model. It is designed to better handle more complex, instruction-based tasks and provide more accurate responses across a wider range of topics.
  • Intended Users: Researchers, developers, and AI enthusiasts interested in exploring the capabilities and performance of enhanced instruction-based models.
  • Out-of-Scope Use Cases: This model is not intended for high-stakes decision-making or any usage requiring fail-safe performance, as it is experimental in nature.

Model Architecture

  • Base Model: microsoft/Phi-3-mini-4k-instruct but expanded with more layers
  • Modifications: This model includes additional training layers and an expanded dataset to improve understanding and response generation across diverse instructions.