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 Pro Llama 3 8B AWQ by solidrust

 »  All LLMs  »  solidrust  »  Hermes 2 Pro Llama 3 8B AWQ   URL Share it on

  474   
  4-bit   Autotrain compatible   Awq   Axolotl Base model:nousresearch/hermes... Base model:quantized:nousresea...   Chatml   Conversational   Dataset:teknium/openhermes-2.5   Distillation   Dpo   En   Endpoints compatible   Finetuned   Function calling   Gpt4   Instruct   Json mode   Llama   Llama-3   Quantized   Region:us   Rlhf   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/solidrust/Hermes-2-Pro-Llama-3-8B-AWQ 

Hermes 2 Pro Llama 3 8B AWQ Benchmarks

ARC: 63.48 vs 96.7 (so35)-34.4%
HellaSwag: 83.22 vs 95.3 (gpt4)-12.7%
MMLU: 64.8 vs 88.3 (so35)-26.6%
TruthfulQA: 56.56 vs 59 (gpt4)-4.1%
WinoGrande: 76.4 vs 87.5 (gpt4)-12.7%
GSM8K: 67.93 vs 96.4 (so35)-29.5%
LLME Score: 0.22377
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hermes 2 Pro Llama 3 8B AWQ (solidrust/Hermes-2-Pro-Llama-3-8B-AWQ)

Hermes 2 Pro Llama 3 8B AWQ Parameters and Internals

Model Type 
text-generation, instruct, chatml, DPO, RLHF, gpt4
Additional Notes 
Hermes 2 Pro is an upgraded version with agentic capabilities enabled by single-token mystifying symbols.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
OpenHermes 2.5, Function Calling and JSON Mode dataset, in-house datasets
Methodology:
Retrained version with Function Calling and JSON Structured Outputs improvements
Input Output 
Input Format:
Custom prompt format using chatml
Accepted Modalities:
text
Output Format:
Text
LLM NameHermes 2 Pro Llama 3 8B AWQ
Repository 🤗https://huggingface.co/solidrust/Hermes-2-Pro-Llama-3-8B-AWQ 
Base Model(s)  Hermes 2 Pro Llama 3 8B   NousResearch/Hermes-2-Pro-Llama-3-8B
Model Size8b
Required VRAM5.8 GB
Updated2024-12-22
Maintainersolidrust
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128288
Torch Data Typefloat16

Best Alternatives to Hermes 2 Pro Llama 3 8B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB150
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB321
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB154
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB120
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB150
Llama 3 8B Instruct AWQ8K / 5.8 GB7822720
Llama 3 ELYZA JP 8B AWQ8K / 5.8 GB19893
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB13304
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB12710
Meta Llama 3 8B AWQ8K / 5.8 GB28070
Note: green Score (e.g. "73.2") means that the model is better than solidrust/Hermes-2-Pro-Llama-3-8B-AWQ.

Rank the Hermes 2 Pro Llama 3 8B AWQ 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