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

BigMistral 13B GLUED by athirdpath

 »  All LLMs  »  athirdpath  »  BigMistral 13B GLUED   URL Share it on

  14   
  Autotrain compatible   Endpoints compatible   Mistral   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/athirdpath/BigMistral-13b-GLUED 

BigMistral 13B GLUED Benchmarks

LLME Score: 0.15704
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
BigMistral 13B GLUED (athirdpath/BigMistral-13b-GLUED)

BigMistral 13B GLUED Parameters and Internals

Model Type 
base model, LoRA enhanced
Additional Notes 
The model involves a 512-rank LORA trained over BigMistral-13b using a modified training method focused on 'healing' the 13b merge. Results are preliminary and show potential for improvement.
Training Details 
Data Sources:
teknium1’s roleplay-instruct-v2.1, private Elieithyia dataset, HF’s No Robots
Methodology:
Modified NeverSleep recipe with increased gradient accumulation steps, lowered learning rate, and decreased dropout.
LLM NameBigMistral 13B GLUED
Repository 🤗https://huggingface.co/athirdpath/BigMistral-13b-GLUED 
Model Size13b
Required VRAM26.6 GB
Updated2024-12-22
Maintainerathirdpath
Model Typemistral
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   5.0 GB: 5-of-6   1.9 GB: 6-of-6
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to BigMistral 13B GLUED

Best Alternatives
Context / RAM
Downloads
Likes
LuminRP 13B 128K V0.5128K / 25.1 GB192
Breeze 13B 32K Instruct V1.032K / 25.6 GB170
Power WizardLM 2 13B32K / 25 GB152
Mistral V0.3 13B 32K Base V132K / 25.2 GB160
Breeze 13B 32K Base V1.032K / 25.6 GB140
Pandora 13B V132K / 24.9 GB10970
Pandora V1 13B32K / 24.9 GB163
BigMistral 13B32K / 26.7 GB162
...stral 13B DARE Blended FAILURE32K / 26.7 GB160
...stral 13B DARE Blended FAILURE32K / 26.7 GB150
Note: green Score (e.g. "73.2") means that the model is better than athirdpath/BigMistral-13b-GLUED.

Rank the BigMistral 13B GLUED 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? 40066 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 v20241217
  Support LLM Explorer