README.md

metadata

license: apache-2.0
language:
  - en
metrics:
  - accuracy
  - code_eval
library_name: transformers
pipeline_tag: text-generation
tags:
  - rag
  - context obedient
  - TroyDoesAI
  - Mermaid
  - Flow
  - Diagram
  - Sequence
  - Map
  - Context
  - Accurate
  - Summarization
  - Story
  - Code
  - Coder
  - Architecture
  - Retrieval
  - Augmented
  - Generation
  - AI
  - LLM
  - Mistral
  - LLama
  - Large Language Model
  - Retrieval Augmented Generation
  - Troy Andrew Schultz
  - LookingForWork
  - OpenForHire
  - IdoCoolStuff
  - Knowledge Graph
  - Knowledge
  - Graph
  - Accelerator
  - Enthusiast
  - Chatbot
  - Personal Assistant
  - Copilot
  - lol
  - tags
  - Pruned
  - efficient
  - smaller
  - small
  - local
  - open
  - source
  - open source
  - quant
  - quantize
  - ablated
  - Ablation
  - 'uncensored '
  - unaligned
  - 'bad '
  - alignment

For those trying to shoe horn this large model on your machine every GB of saved memory counts when offloading to System RAM!

Here is a pruned down the 22.2 Billion parameter model by 2 junk layers to make a 21.5B that doesnt appear to lose any sense of quality.

https://huggingface.co/mistralai/Codestral-22B-v0.1