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

TherapyLlama 8B V1 by victunes

 »  All LLMs  »  victunes  »  TherapyLlama 8B V1   URL Share it on

  80   
  Autotrain compatible   Conversational Dataset:victunes/nart-100k-syn...   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/victunes/TherapyLlama-8B-v1 

TherapyLlama 8B V1 Benchmarks

LLME Score: 0.1842
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TherapyLlama 8B V1 (victunes/TherapyLlama-8B-v1)

TherapyLlama 8B V1 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
self-discovery, emotional support
Applications:
therapy aid, mental health support
Primary Use Cases:
mimicking empathy, simulating therapy sessions
Limitations:
not a substitute for professional therapy
Considerations:
Models AI empathy and understanding but is not self-aware.
Additional Notes 
TherapyLlama 8B v1, also known as Buddy, is designed to mimic empathy and therapeutic inquiry. It is explicitly not a substitute for licensed mental health professionals.
Supported Languages 
English (fluent)
Training Details 
Data Sources:
victunes/nart-100k-synthetic-buddy-mixed-names, jerryjalapeno/nart-100k-synthetic
Data Volume:
100K prompts and responses
Methodology:
fine-tuned on Llama 3 8B with a modified Vicuna 1.1 format
Model Architecture:
Llama architecture
Responsible Ai Considerations 
Accountability:
victunes
Mitigation Strategies:
User disclaimers advise that the model is not a real therapist.
Input Output 
Input Format:
Vicuna 1.1 format
Accepted Modalities:
text
Output Format:
text-based responses following empathy simulation
Performance Tips:
Invoke role-play mode by saying 'You are Socrates'.
LLM NameTherapyLlama 8B V1
Repository 🤗https://huggingface.co/victunes/TherapyLlama-8B-v1 
Model Size8b
Required VRAM16.1 GB
Updated2025-02-22
Maintainervictunes
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
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 TherapyLlama 8B V1

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB3927680
Mpasila Viking 8B1024K / 16.1 GB840
Hel V2 8B DARK FICTION1024K / 16.1 GB220
161024K / 16.1 GB1690
...di95 LewdStorytellerMix 8B 64K1024K / 16.1 GB692
Because Im Bored Nsfw11024K / 16.1 GB361
121024K / 16.1 GB600
MrRoboto ProLong 8B V4b1024K / 16.1 GB1070
MrRoboto ProLong 8B V1a1024K / 16.1 GB1080
MrRoboto ProLong 8B V2a1024K / 16.1 GB1020
Note: green Score (e.g. "73.2") means that the model is better than victunes/TherapyLlama-8B-v1.

Rank the TherapyLlama 8B V1 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? 43508 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