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

Hermes 2 Theta Llama 3 8B EXL2 4.75bpw by mpasila

 »  All LLMs  »  mpasila  »  Hermes 2 Theta Llama 3 8B EXL2 4.75bpw   URL Share it on

  7   
  Autotrain compatible   Axolotl Base model:finetune:nousresear... Base model:nousresearch/hermes...   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   Synthetic data
Model Card on HF 🤗: https://huggingface.co/mpasila/Hermes-2-Theta-Llama-3-8B-exl2-4.75bpw 

Hermes 2 Theta Llama 3 8B EXL2 4.75bpw Benchmarks

LLME Score: 0.19686
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hermes 2 Theta Llama 3 8B EXL2 4.75bpw (mpasila/Hermes-2-Theta-Llama-3-8B-exl2-4.75bpw)

Hermes 2 Theta Llama 3 8B EXL2 4.75bpw Parameters and Internals

Model Type 
text generation, chat
Additional Notes 
This is an ExLlamaV2 quantized model in 4.75bpw configuration.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
teknium/OpenHermes-2.5
Methodology:
Merged and further RLHF'ed version of Hermes 2 Pro model and Meta's Llama-3 Instruct model using chatml and function calling techniques.
Context Length:
8192
Input Output 
Input Format:
ChatML format
Accepted Modalities:
text
Output Format:
JSON and text responses
Performance Tips:
Enable 'add_generation_prompt' for continued assistant response.
Release Notes 
Version:
2-Theta
Notes:
First experimental merged model combining Hermes 2 Pro and Meta's Llama-3 Instruct.
LLM NameHermes 2 Theta Llama 3 8B EXL2 4.75bpw
Repository 🤗https://huggingface.co/mpasila/Hermes-2-Theta-Llama-3-8B-exl2-4.75bpw 
Base Model(s)  Hermes 2 Pro Llama 3 8B   NousResearch/Hermes-2-Pro-Llama-3-8B
Model Size8b
Required VRAM5.6 GB
Updated2024-12-22
Maintainermpasila
Model Typellama
Model Files  5.6 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
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 Hermes 2 Theta Llama 3 8B EXL2 4.75bpw

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 mpasila/Hermes-2-Theta-Llama-3-8B-exl2-4.75bpw.

Rank the Hermes 2 Theta Llama 3 8B EXL2 4.75bpw 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? 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