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

ECE TW3 JRGL V5 by paloalma

 »  All LLMs  »  paloalma  »  ECE TW3 JRGL V5   URL Share it on

  1394   
  Merged Model   Autotrain compatible   Endpoints compatible   Ibivibiv/alpaca-dragon-72b-v1   Llama   Lora   Moreh/momo-72b-lora-1.8.7-dpo   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/paloalma/ECE-TW3-JRGL-V5 

ECE TW3 JRGL V5 Benchmarks

MMLU Pro: 40.53
GPQA: 12.19
MUSR: 16.89
BBH: 43.46
IFEval: 45.53 vs 88 (so35)-48.3%
MATH Lvl 5: 18.13
LLME Score: 0.28925
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ECE TW3 JRGL V5 (paloalma/ECE-TW3-JRGL-V5)

ECE TW3 JRGL V5 Parameters and Internals

Additional Notes 
This model is a "merge" type, specifically created using the MergeKit tool by combining two specified models: moreh/MoMo-72B-lora-1.8.7-DPO and ibivibiv/alpaca-dragon-72b-v1.
LLM NameECE TW3 JRGL V5
Repository 🤗https://huggingface.co/paloalma/ECE-TW3-JRGL-V5 
Merged ModelYes
Model Size72b
Required VRAM159.6 GB
Updated2025-02-05
Maintainerpaloalma
Model Typellama
Model Files  5.0 GB: 1-of-82   3.8 GB: 2-of-82   3.5 GB: 3-of-82   3.8 GB: 4-of-82   3.5 GB: 5-of-82   3.5 GB: 6-of-82   3.5 GB: 7-of-82   3.8 GB: 8-of-82   3.2 GB: 9-of-82   3.5 GB: 10-of-82   3.5 GB: 11-of-82   3.8 GB: 12-of-82   3.2 GB: 13-of-82   3.5 GB: 14-of-82   3.5 GB: 15-of-82   3.8 GB: 16-of-82   3.2 GB: 17-of-82   3.5 GB: 18-of-82   3.5 GB: 19-of-82   3.8 GB: 20-of-82   3.2 GB: 21-of-82   3.5 GB: 22-of-82   3.5 GB: 23-of-82   3.8 GB: 24-of-82   3.2 GB: 25-of-82   3.5 GB: 26-of-82   3.5 GB: 27-of-82   3.8 GB: 28-of-82   3.2 GB: 29-of-82   3.5 GB: 30-of-82   3.5 GB: 31-of-82   3.8 GB: 32-of-82   3.2 GB: 33-of-82   3.5 GB: 34-of-82   3.5 GB: 35-of-82   3.8 GB: 36-of-82   3.2 GB: 37-of-82   3.5 GB: 38-of-82   3.5 GB: 39-of-82   3.8 GB: 40-of-82   3.2 GB: 41-of-82   3.5 GB: 42-of-82   3.5 GB: 43-of-82   3.8 GB: 44-of-82   3.2 GB: 45-of-82
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Vocabulary Size152064
LoRA ModelYes
Torch Data Typefloat32

Best Alternatives to ECE TW3 JRGL V5

Best Alternatives
Context / RAM
Downloads
Likes
Smaug 72B V0.132K / 144.5 GB3129468
TW3 JRGL V232K / 79.7 GB38840
Le Triomphant ECE TW332K / 79.7 GB41264
MoMo 72B Lora 1.8.7 DPO32K / 208.5 GB247068
Rhea 72B V0.532K / 144.5 GB4203134
JuliusCesar 72B BeyonderV.032K / 74.2 GB530
ECE TW3 JRGL V332K / 77.8 GB30250
ECE TW3 JRGL V432K / 77.8 GB30240
Caigun Model 72B KGI32K / 144.6 GB180
Alpaca Dragon 72B V132K / 203.7 GB146625
Note: green Score (e.g. "73.2") means that the model is better than paloalma/ECE-TW3-JRGL-V5.

Rank the ECE TW3 JRGL V5 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? 42577 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