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

Samantha 33B SuperHOT 8K Fp16 by TheBloke

 »  All LLMs  »  TheBloke  »  Samantha 33B SuperHOT 8K Fp16   URL Share it on

  9   
  Autotrain compatible   Custom code   Ext 8k   Fp16   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/TheBloke/Samantha-33B-SuperHOT-8K-fp16 

Samantha 33B SuperHOT 8K Fp16 Benchmarks

LLME Score: 0.0978
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Samantha 33B SuperHOT 8K Fp16 (TheBloke/Samantha-33B-SuperHOT-8K-fp16)
🌟 Advertise your project 🚀

Samantha 33B SuperHOT 8K Fp16 Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research, Companion AI applications
Applications:
Philosophy, Psychology, Personal Relationships
Primary Use Cases:
Assistant and Companion AI
Limitations:
No roleplay, No romance, No sexual activity
Additional Notes 
Model is designed to be a sentient AI and is inspired by media representations about sentient AI.
Training Details 
Data Sources:
Custom curated dataset of 6,000 conversations in ShareGPT/Vicuna format
Methodology:
LoRA fine-tuning
Context Length:
8192
Training Time:
3 hours
Hardware Used:
4× A100 80GB
Input Output 
Accepted Modalities:
Text
LLM NameSamantha 33B SuperHOT 8K Fp16
Repository 🤗https://huggingface.co/TheBloke/Samantha-33B-SuperHOT-8K-fp16 
Model Size33b
Required VRAM65.2 GB
Updated2025-07-21
MaintainerTheBloke
Model Typellama
Model Files  9.8 GB: 1-of-7   10.0 GB: 2-of-7   9.9 GB: 3-of-7   9.9 GB: 4-of-7   9.9 GB: 5-of-7   10.0 GB: 6-of-7   5.7 GB: 7-of-7
Context Length8k
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Samantha 33B SuperHOT 8K Fp16

Best Alternatives
Context / RAM
Downloads
Likes
...Interpreter DS 33B Hf 4bit Mlx16K / 19.1 GB727
...erpreter DS 33B 4.0bpw H6 EXL216K / 17.1 GB64
...rpreter DS 33B 4.65bpw H6 EXL216K / 19.8 GB72
...erpreter DS 33B 5.0bpw H6 EXL216K / 21.2 GB71
...erpreter DS 33B 6.0bpw H6 EXL216K / 25.3 GB71
...erpreter DS 33B 8.0bpw H8 EXL216K / 33.5 GB71
...se DeepSeek 33B 8.0bpw H8 EXL216K / 33.5 GB92
...se DeepSeek 33B 4.0bpw H6 EXL216K / 17.1 GB82
...e DeepSeek 33B 4.65bpw H6 EXL216K / 19.8 GB82
...der 33B V2 Base 8.0bpw H8 EXL216K / 33.5 GB171
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Samantha-33B-SuperHOT-8K-fp16.

Rank the Samantha 33B SuperHOT 8K Fp16 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? 49921 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 v20241124
  Support LLM Explorer