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 Llama 2 7B GGML by TheBloke

 »  All LLMs  »  TheBloke  »  Nous Hermes Llama 2 7B GGML   URL Share it on

  36   
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-Llama-2-7B-GGML 

Nous Hermes Llama 2 7B GGML Benchmarks

LLME Score: 0.1209
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nous Hermes Llama 2 7B GGML (TheBloke/Nous-Hermes-Llama-2-7B-GGML)

Nous Hermes Llama 2 7B GGML Parameters and Internals

Model Type 
llama
Additional Notes 
This model is fine-tuned for long responses, lower hallucination rate, and absence of OpenAI censorship mechanisms. The GGML format is deprecated and replaced by GGUF.
Training Details 
Data Sources:
GPTeacher by Teknium, Wizard LM by nlpxucan, Nous Research Instruct Dataset by Karan4D and HueminArt, GPT4-LLM and Unnatural Instructions by Microsoft, Airoboros dataset by jondurbin, Camel-AI's domain expert datasets, CodeAlpaca dataset by Sahil 2801
Methodology:
Fine-tuned on over 300,000 instructions using synthetic GPT-4 outputs
Context Length:
4096
Hardware Used:
8x a100 80GB DGX machine
LLM NameNous Hermes Llama 2 7B GGML
Repository 🤗https://huggingface.co/TheBloke/Nous-Hermes-Llama-2-7B-GGML 
Model NameNous Hermes Llama 2 7B
Model CreatorNousResearch
Base Model(s)  Nous Hermes Llama 2 7B   NousResearch/Nous-Hermes-llama-2-7b
Model Size7b
Required VRAM2.9 GB
Updated2025-02-22
MaintainerTheBloke
Model Typellama
Model Files  2.9 GB   3.6 GB   3.3 GB   3.0 GB   3.8 GB   4.2 GB   4.1 GB   3.8 GB   4.6 GB   5.1 GB   4.8 GB   4.7 GB   5.5 GB   7.2 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Nous Hermes Llama 2 7B GGML

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 7B Chat GGML0K / 2.9 GB2986867
Llama 2 GGML Medical Chatbot0K /  GB31434
Llama 2 7B GGML0K / 2.9 GB866220
CodeLlama 7B GGML0K / 3 GB4227
CodeLlama 7B Instruct GGML0K / 3 GB4420
Yarn Llama 2 7B 128K GGML0K / 2.9 GB86
CodeLlama 7B Python GGML0K / 2.9 GB3123
Yarn Llama 2 7B 64K GGML0K / 2.9 GB73
Airoboros L2 7B 2.1 GGML0K / 2.9 GB71
Zarafusionex 1.1 L2 7B GGML0K / 2.9 GB22
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Nous-Hermes-Llama-2-7B-GGML.

Rank the Nous Hermes Llama 2 7B 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? 43508 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