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

Opus V1.4 70B Llama3 EXL2 2.25bpw H6 by dreamgen

 »  All LLMs  »  dreamgen  »  Opus V1.4 70B Llama3 EXL2 2.25bpw H6   URL Share it on

  6   
  Autotrain compatible   Axolotl   Conversational   En   Endpoints compatible   Exl2   Instruct   Llama   Pytorch   Quantized   Region:us   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/dreamgen/opus-v1.4-70b-llama3-exl2-2.25bpw-h6 

Opus V1.4 70B Llama3 EXL2 2.25bpw H6 Benchmarks

LLME Score: 0.19328
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Opus V1.4 70B Llama3 EXL2 2.25bpw H6 (dreamgen/opus-v1.4-70b-llama3-exl2-2.25bpw-h6)

Opus V1.4 70B Llama3 EXL2 2.25bpw H6 Parameters and Internals

Model Type 
story-writing, role-playing
Use Cases 
Areas:
research, entertainment
Applications:
story-writing, role-playing
Primary Use Cases:
Written content creation, Interactive storytelling
Limitations:
Personal use only, not permitted for commercial use.
Additional Notes 
The model supports versatile writing tasks and general assistance beyond story-writing and role-playing.
Training Details 
Data Sources:
Human-written text for story-writing and role-playing
Data Volume:
Over 100M tokens
Context Length:
8192
Input Output 
Input Format:
Extended Llama 3 prompt format with `writer` roles for characters
Accepted Modalities:
text
Output Format:
Text-based story or role-play output
Performance Tips:
For story-writing and role-play, use Min P-based sampling with min_p in the range [0.01, 0.1] and temperature in the range [0.5, 1.5].
LLM NameOpus V1.4 70B Llama3 EXL2 2.25bpw H6
Repository 🤗https://huggingface.co/dreamgen/opus-v1.4-70b-llama3-exl2-2.25bpw-h6 
Model Size70b
Required VRAM22.2 GB
Updated2025-02-22
Maintainerdreamgen
Model Typellama
Instruction-BasedYes
Model Files  8.5 GB: 1-of-3   8.6 GB: 2-of-3   5.1 GB: 3-of-3
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-nd-4.0
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Opus V1.4 70B Llama3 EXL2 2.25bpw H6

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB75
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB63
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB52
...0B Instruct Gradient 262K 4bit256K / 39.7 GB93
...0B Instruct Gradient 262K 8bit256K / 75 GB72
...0B Instruct Gradient 262K 2bit256K / 21.9 GB51
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB50
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB81
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB70
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB60

Rank the Opus V1.4 70B Llama3 EXL2 2.25bpw H6 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? 43470 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