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

Nous Hermes Llama2 GGML by TheBloke

 »  All LLMs  »  TheBloke  »  Nous Hermes Llama2 GGML   URL Share it on

  5   
Base model:finetune:nousresear... Base model:nousresearch/nous-h...   Distillation   En   Ggml   Llama   Llama2   Quantized   Region:us   Self-instruct   Synthetic instruction
Model Card on HF 🤗: https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GGML 

Nous Hermes Llama2 GGML Benchmarks

LLME Score: 0.10577
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nous Hermes Llama2 GGML (TheBloke/Nous-Hermes-Llama2-GGML)
🌟 Advertise your project 🚀

Nous Hermes Llama2 GGML Parameters and Internals

Model Type 
llama
Additional Notes 
The model is fine-tuned on over 300,000 instructions with a focus on long responses, and a lower hallucination rate. Original model data from synthetic GPT-4 outputs allow it to perform well in knowledge, task completion, and style. The model follows the Alpaca prompt format.
Training Details 
Data Sources:
GPT-4 outputs, GPTeacher, Wizard LM, Nous Research Instruct Dataset, GPT4-LLM, Unnatural Instructions, Airoboros dataset, Camel-AI's domain expert datasets, CodeAlpaca dataset
Methodology:
Fine-tuning on over 300,000 instructions using Alpaca format
Context Length:
4096
Hardware Used:
8x A100 80GB DGX machine
LLM NameNous Hermes Llama2 GGML
Repository 🤗https://huggingface.co/TheBloke/Nous-Hermes-Llama2-GGML 
Model NameNous Hermes Llama 2 13B
Model CreatorNousResearch
Base Model(s)  Nous Hermes Llama2 13B   NousResearch/Nous-Hermes-Llama2-13b
Model Size13b
Required VRAM5.7 GB
Updated2025-08-16
MaintainerTheBloke
Model Typellama
Model Files  5.7 GB   7.1 GB   6.5 GB   5.9 GB   7.3 GB   8.1 GB   8.1 GB   7.6 GB   8.9 GB   9.8 GB   9.4 GB   9.2 GB   10.8 GB   13.8 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Nous Hermes Llama2 GGML

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 13B Chat GGML0K / 5.5 GB86698
RuGPT 3.5 13B GGML0K / 7.4 GB38
RuGPT 3.5 13B GGML0K / 7.4 GB714
MythoMax L2 13B GGML0K / 5.5 GB1482
Yarn Llama 2 13B 128K GGML0K / 5.5 GB156
...rca Platypus WizardLM 13B GGML0K / 5.5 GB46
...zardCoder Python 13B V1.0 GGML0K / 5.7 GB1322
...penBuddy Llama2 13B V11.1 GGML0K / 5.5 GB25
Stheno L2 13B GGML0K / 5.5 GB125
Yarn Llama 2 13B 64K GGML0K / 5.5 GB65
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Nous-Hermes-Llama2-GGML.

Rank the Nous Hermes Llama2 GGML 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? 50723 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 v20241124
  Support LLM Explorer