metadata

base_model: meta-llama/Llama-3.1-8B-Instruct
library_name: transformers
tags:
  - llama
  - llama3
  - llama-ti
  - fluently-lm
  - fluently-merge
  - chat
  - conversational
  - reflection
  - reasoning
  - math
  - writing
pipeline_tag: text-generation
language:
  - en
  - code
license: apache-2.0

Llama3.1 8B TI Instruct

Llama TI is an improved Llama (from Meta AI), some aspects of the model have been revised and some features have been added.

Info

Main

The model is based on Meta-Llama-3.1-8B-Instruct, and has the same 8.03B parameters. The Llama3 architecture (LlamaForCausalLM) has been preserved and the model launch methods are the same.

Differences

Thanks to additional training and advanced merging, it was possible to improve mathematical, biological, reasoning and writing skills.

Now the model can:

Count well and solve mathematical/physical problems
Reason/think logically
Write creatively (in many languages)
Code well
Process/analyze large texts

Where is the base version?

It is available here!

Special thanks to:

Meta AI, NVIDIA, Arcee AI, SkyWork, NousReaserch, Unsloth and Project Fluently.

Developed and uploaded by ehristoforu.