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

NousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2 by Zoyd

 ยป  All LLMs  ยป  Zoyd  ยป  NousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2   URL Share it on

  12   
  Autotrain compatible   Axolotl Base model:nousresearch/hermes... Base model:quantized:nousresea...   Chatml   Conversational   Dataset:teknium/openhermes-2.5   Distillation   Dpo   En   Endpoints compatible   Exl2   Finetuned   Function calling   Gpt4   Instruct   Json mode   Llama   Llama-3   Merges   Quantized   Region:us   Rlhf   Safetensors   Synthetic data
Model Card on HF ๐Ÿค—: https://huggingface.co/Zoyd/NousResearch_Hermes-2-Theta-Llama-3-8B-6_5bpw_exl2 

NousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2 Benchmarks

LLME Score: 0.19966
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2 (Zoyd/NousResearch_Hermes-2-Theta-Llama-3-8B-6_5bpw_exl2)

NousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2 Parameters and Internals

Model Type 
instruct, chatml, DPO, RLHF, gpt4 synthetic data, distillation, function calling, json mode
Use Cases 
Areas:
research, commercial applications
Applications:
chatbots, instruction following, function calling
Primary Use Cases:
multi-turn chat dialogue, function calling, structured JSON responses
Limitations:
Complexity in function calling setup
Considerations:
Consider special tokens and role formats when setting up prompts.
Additional Notes 
Quantized versions available using GGUF.
Supported Languages 
primary (en)
Training Details 
Data Sources:
teknium/OpenHermes-2.5
Data Volume:
Not specified
Methodology:
Merged and further RLHF'ed version combining Hermes 2 Pro and Meta's Llama-3 Instruct
Context Length:
2048
Training Time:
Not specified
Model Architecture:
Hermes-2 ฮ˜ is a merged model combining Hermes 2 Pro and Meta's Llama-3 Instruct.
Input Output 
Input Format:
ChatML format with system and user roles defined
Accepted Modalities:
text
Output Format:
Text responses, structured JSON
Performance Tips:
Utilize ChatML or the prompt structure for function calling for optimal engagement.
Release Notes 
Version:
Initial release
Date:
Not specified
Notes:
Merged model of Hermes 2 Pro and Meta's Llama-3 with enhancements for instruct and chat applications.
LLM NameNousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2
Repository ๐Ÿค—https://huggingface.co/Zoyd/NousResearch_Hermes-2-Theta-Llama-3-8B-6_5bpw_exl2 
Base Model(s)  Hermes 2 Pro Llama 3 8B   NousResearch/Hermes-2-Pro-Llama-3-8B
Model Size8b
Required VRAM7.2 GB
Updated2024-12-22
MaintainerZoyd
Model Typellama
Model Files  7.2 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to NousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB152
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB121
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB82
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1425
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB3417
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB143
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB91
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB141
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB91
Note: green Score (e.g. "73.2") means that the model is better than Zoyd/NousResearch_Hermes-2-Theta-Llama-3-8B-6_5bpw_exl2.

Rank the NousResearch Hermes 2 Theta Llama 3 8B 6 5bpw EXL2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40123 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 v20241217
  Support LLM Explorer