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

Thesa by johnhandleyd

 »  All LLMs  »  johnhandleyd  »  Thesa   URL Share it on

  7   
  Adapter Base model:adapter:thebloke/ze... Base model:thebloke/zephyr-7b-... Dataset:loaiabdalslam/counselc...   En   Finetuned   Generated from trainer   Gptq   Lora   Peft   Quantized   Region:us   Safetensors   Tensorboard

Thesa Benchmarks

LLME Score: 0.17712
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Thesa Parameters and Internals

Model Type 
text-generation
Use Cases 
Limitations:
This model is purely experimental and should not be used as substitute for a mental health professional.
Additional Notes 
Thesa is an experimental project of a therapy chatbot trained on mental health data and fine-tuned with the Zephyr GPTQ model that uses quantization to decrease high computatinal and storage costs.
Supported Languages 
en (English)
Training Details 
Data Sources:
loaiabdalslam/counselchat
Methodology:
fine-tuned from TheBloke/zephyr-7B-alpha-GPTQ on various mental health datasets
LLM NameThesa
Repository 🤗https://huggingface.co/johnhandleyd/thesa 
Base Model(s)  Zephyr 7B Alpha GPTQ   TheBloke/zephyr-7B-alpha-GPTQ
Model Size7b
Required VRAM0 GB
Updated2024-11-21
Maintainerjohnhandleyd
Model Files  0.0 GB   0.0 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureAdapter
Licensemit
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj
LoRA Alpha16
LoRA Dropout0.05
R Param16
Thesa (johnhandleyd/thesa)

Best Alternatives to Thesa

Best Alternatives
Context / RAM
Downloads
Likes
Term Qwen2 7 Json Lora0K / 0.1 GB130
LMS Chatbot0K / 0 GB50
Llama 2 7B Chat Text2code0K / 0 GB194
Zephyr 7B Alpha GPTQ0K / 0 GB21
Selfbot 256 Mistral0K / 0.4 GB50
Futadom Mistral0K / 0.2 GB31
Humiliation Mistral0K / 0.2 GB21
Zephyr Finetuned Legal0K / 0 GB101
Typhoon 7B Chat Alpaca0K / 0 GB144
Mistral MetaMath0070K / 0 GB51
Note: green Score (e.g. "73.2") means that the model is better than johnhandleyd/thesa.

Rank the Thesa 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? 38199 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 v20241110
  Support LLM Explorer