LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama2 22B GPLATTY GGUF by TheBloke

 »  All LLMs  »  TheBloke  »  Llama2 22B GPLATTY GGUF   URL Share it on

  116   
Base model:grimpep/llama2-22b-... Base model:quantized:grimpep/l...   Gguf   Llama   Llama2   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGUF 

Llama2 22B GPLATTY GGUF Benchmarks

LLME Score: 0.13213
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama2 22B GPLATTY GGUF (TheBloke/Llama2-22B-GPLATTY-GGUF)

Llama2 22B GPLATTY GGUF Parameters and Internals

Model Type 
llama
Additional Notes 
This model is an experiment using the frankenstein script from https://huggingface.co/chargoddard/llama2-22b. It merges an already merged 13B Llama v2 model (GUACHAT + KIMIKO). Then used https://huggingface.co/TheBloke/GPlatty-30B-SuperHOT-8K-fp16 as donor model. It used 160GB of system ram to merge these models, without swap. It exhibits no strange behavior when generating, but more hallucinations than usual might occur. The model is experimental and might be more ethically aligned than other versions.
LLM NameLlama2 22B GPLATTY GGUF
Repository 🤗https://huggingface.co/TheBloke/Llama2-22B-GPLATTY-GGUF 
Model NameLlama2 22B GPLATTY
Model Creatorgrimpep
Base Model(s)  grimpep/llama2-22B-GPLATTY   grimpep/llama2-22B-GPLATTY
Model Size22b
Required VRAM9.1 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  9.1 GB   11.6 GB   10.6 GB   9.5 GB   12.3 GB   13.2 GB   12.4 GB   15.0 GB   15.5 GB   15.0 GB   17.9 GB   23.2 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Llama2 22B GPLATTY GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Codestral 22B V0.1 GGUF0K / 4.8 GB1409
...t2cypher Codestral Q4 K M Gguf0K / 13.3 GB194
...xt2cypher Codestral 16bit Gguf0K / 44.5 GB280
Qwen1.5 22B Chat Merge GGUF0K / 12.6 GB181
Nucleus 22B Token 500B GGUF0K / 9.1 GB403
Llama2 22B Daydreamer V3 GGUF0K / 9.1 GB1662
Llama2 22B Daydreamer V2 GGUF0K / 9.1 GB1461
Huginn 22B Prototype GGUF0K / 9.1 GB962
Huginn 22B Prototype GGML0K / 9.2 GB31
Llama2 22B GPLATTY GGML0K / 9.2 GB97
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama2-22B-GPLATTY-GGUF.

Rank the Llama2 22B GPLATTY GGUF Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42577 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer