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

TIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2 by Zoyd

 »  All LLMs  »  Zoyd  »  TIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2   URL Share it on

  5   
  Arxiv:2405.03548   4-bit   Autotrain compatible   Conversational   En   Endpoints compatible   Exl2   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-7B-Plus-4_0bpw_exl2 

TIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2 Benchmarks

LLME Score: 0.18677
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2 (Zoyd/TIGER-Lab_MAmmoTH2-7B-Plus-4_0bpw_exl2)

TIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2 Parameters and Internals

Model Type 
text generation, instruction tuning
Use Cases 
Areas:
research, commercial applications
Applications:
mathematical reasoning, chatbot development
Primary Use Cases:
reasoning with math problems
Limitations:
Not all mathematical fields comprehensively covered
Considerations:
Performance may vary with complexity and specifics of math problems.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
pre-training web corpus, WEBINSTRUCT dataset
Data Volume:
10 million instruction-response pairs
Methodology:
Fine-tuning on WEBINSTRUCT dataset.
Context Length:
2048
Training Time:
varied based on model size
Hardware Used:
original Llama-3, Mistral base models
Model Architecture:
derived from Llama-3 or Mistral models
Input Output 
Input Format:
text input for math problems
Accepted Modalities:
text
Output Format:
text solution
Performance Tips:
Optimized for reasoning tasks; performance varies with complexity.
Release Notes 
Version:
Plus
Date:
2024
Notes:
Upgraded performance on reasoning tasks with additional datasets.
Version:
Standard
Date:
2023
Notes:
Introduced MAmmoTH2 with fine-tuned instruction responses.
LLM NameTIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2
Repository 🤗https://huggingface.co/Zoyd/TIGER-Lab_MAmmoTH2-7B-Plus-4_0bpw_exl2 
Model Size7b
Required VRAM3.9 GB
Updated2025-02-22
MaintainerZoyd
Model Typemistral
Model Files  3.9 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to TIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...al Nemo Instruct 2407 Bnb 4bit1000K / 8.3 GB1885427
...istral Nemo Base 2407 Bnb 4bit1000K / 8.3 GB987615
...t 3.5 0106 128K 4.0bpw H6 EXL2128K / 3.9 GB81
...t 3.5 0106 128K 8.0bpw H8 EXL2128K / 7.4 GB71
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB15850521
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB2058215
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB2701
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1400532
MistralContinuedFine32K / 14.5 GB14470
Note: green Score (e.g. "73.2") means that the model is better than Zoyd/TIGER-Lab_MAmmoTH2-7B-Plus-4_0bpw_exl2.

Rank the TIGER Lab MAmmoTH2 7B Plus 4 0bpw EXL2 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