Gemma 2 27B It SimPO 37K 100steps by AALF

 ยป  All LLMs  ยป  AALF  ยป  Gemma 2 27B It SimPO 37K 100steps   URL Share it on

  Arxiv:2310.01377   Arxiv:2405.14734   Alignment-handbook   Autotrain compatible Base model:finetune:google/gem... Base model:google/gemma-2-27b-...   Conversational   Endpoints compatible   Gemma2   Generated from trainer   Region:us   Safetensors   Sharded   Tensorflow

Gemma 2 27B It SimPO 37K 100steps Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 2 27B It SimPO 37K 100steps Parameters and Internals

Model Type
text-generation
Training Details
Data Sources:
HuggingFaceH4/ultrafeedback_binarized
Data Volume:37,040 training data points
Methodology:SimPO framework with On-Policy Preference Data Generation
Context Length:2048
Hardware Used:
8x80G A800 GPUs
Input Output
Input Format:Prompts with max length of 1800
Accepted Modalities:
text
Output Format:Text
LLM NameGemma 2 27B It SimPO 37K 100steps
Repository ๐Ÿค—https://huggingface.co/AALF/gemma-2-27b-it-SimPO-37K-100steps 
Base Model(s)  Gemma 2 27B It   google/gemma-2-27b-it
Model Size27b
Required VRAM54.7 GB
Updated2024-11-13
MaintainerAALF
Model Typegemma2
Model Files  4.7 GB: 1-of-12   4.9 GB: 2-of-12   4.9 GB: 3-of-12   5.0 GB: 4-of-12   4.9 GB: 5-of-12   4.9 GB: 6-of-12   5.0 GB: 7-of-12   4.9 GB: 8-of-12   4.9 GB: 9-of-12   5.0 GB: 10-of-12   4.9 GB: 11-of-12   0.7 GB: 12-of-12
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.43.3
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16
Gemma 2 27B It SimPO 37K 100steps (AALF/gemma-2-27b-it-SimPO-37K-100steps)

Best Alternatives to Gemma 2 27B It SimPO 37K 100steps

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2 27B It8K / 54.7 GB245666439
Magnum V4 27B8K / 54.7 GB5338
Gemma 2 27B8K / 108.3 GB19598177
Datagemma Rag 27B It8K / 54.7 GB5352170
Datagemma Rig 27B It8K / 54.7 GB90794
Magnum V3 27B Kto8K / 108.2 GB251411
Gemma 2 27B It Abliterated8K / 54.7 GB252216
Gemma2 Gutenberg 27B8K / 54.7 GB24624
Gemma 2 27B It SimPO 37K8K / 54.7 GB253316
Big Tiger Gemma 27B V18K / 54.7 GB143560
Note: green Score (e.g. "73.2") means that the model is better than AALF/gemma-2-27b-it-SimPO-37K-100steps.

Rank the Gemma 2 27B It SimPO 37K 100steps Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 37901 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110