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

MelloGPT by steve-cse

 »  All LLMs  »  steve-cse  »  MelloGPT   URL Share it on

  748   

MelloGPT is an open-source language model by steve-cse. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: mit, Instruction-Based, HF Score: 57.6, LLM Explorer Score: 0.14, Arc: 53.8, HellaSwag: 76.1, MMLU: 56, TruthfulQA: 55.6, WinoGrande: 73.9, GSM8K: 30.1.

  Conversational Dataset:nbertagnolli/counsel-c...   Endpoints compatible   Instruct   Mistral   Model-index   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/steve-cse/MelloGPT 

MelloGPT Benchmarks

ARC: 53.84 vs 96.7 (so35)-44.3%
HellaSwag: 76.12 vs 95.3 (gpt4)-20.1%
MMLU: 55.99 vs 88.3 (so35)-36.6%
TruthfulQA: 55.61 vs 59 (gpt4)-5.7%
WinoGrande: 73.88 vs 87.5 (gpt4)-15.6%
GSM8K: 30.1 vs 96.4 (so35)-68.8%
LLME Score: 0.1417
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MelloGPT (steve-cse/MelloGPT)
🌟 Advertise your project 🚀

MelloGPT Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
mental health counseling
Applications:
support during mental health concerns
Primary Use Cases:
mental health counseling conversations
Limitations:
Not a replacement for professional mental health assistance
Considerations:
Seek support from qualified professionals for personalized care.
Additional Notes 
A fine-tuned version focused on mental health counseling.
Training Details 
Data Sources:
nbertagnolli/counsel-chat
Methodology:
Fine-tuned on mental health counseling conversations with ethical considerations and privacy sensitivity.
Input Output 
Input Format:
[INST] {prompt} [/INST]
Accepted Modalities:
text
Output Format:
Text responses for counseling prompts.
LLM NameMelloGPT
Repository 🤗https://huggingface.co/steve-cse/MelloGPT 
Model Size7b
Required VRAM14.4 GB
Updated2026-04-02
Maintainersteve-cse
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the MelloGPT

Model
Likes
Downloads
VRAM
MelloGPT GGUF63253 GB
MelloGPT AWQ324 GB
MelloGPT GPTQ164 GB

Best Alternatives to MelloGPT

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
SpydazWeb AI HumanAI RP512K / 14.4 GB141
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB60
...1 Summarize 64K LoRANET Merged128K / 14.4 GB60
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB3538001828
Mistral 7B Instruct V0.232K / 14.4 GB57590
Mixtral AI CyberCoder32K / 14.3 GB00
Note: green Score (e.g. "73.2") means that the model is better than steve-cse/MelloGPT.

Rank the MelloGPT 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? 52509 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer