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

Gemma 7B Zephyr Sft by wandb

 »  All LLMs  »  wandb  »  Gemma 7B Zephyr Sft   URL Share it on

  7   
  Autotrain compatible Base model:finetune:google/gem...   Base model:google/gemma-7b   Conversational Dataset:huggingfaceh4/ultracha...   Endpoints compatible   Gemma   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/wandb/gemma-7b-zephyr-sft 

Gemma 7B Zephyr Sft Benchmarks

ARC: 61.43 vs 96.7 (so35)-36.5%
HellaSwag: 80.73 vs 95.3 (gpt4)-15.3%
MMLU: 60.33 vs 88.3 (so35)-31.7%
TruthfulQA: 43.35 vs 59 (gpt4)-26.5%
WinoGrande: 74.19 vs 87.5 (gpt4)-15.2%
GSM8K: 49.81 vs 96.4 (so35)-48.3%
LLME Score: 0.15947
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 7B Zephyr Sft (wandb/gemma-7b-zephyr-sft)
🌟 Advertise your project 🚀

Gemma 7B Zephyr Sft Parameters and Internals

Model Type 
GPT-like, text-generation
Additional Notes 
The Zephyr SFT recipe applied on top of Gemma 7B
Supported Languages 
primary (English)
Training Details 
Data Sources:
synthetic datasets
Methodology:
Used the alignment handbook recipe with W&B logging
Hardware Used:
8xA100 80GB node by Lambda Labs
LLM NameGemma 7B Zephyr Sft
Repository 🤗https://huggingface.co/wandb/gemma-7b-zephyr-sft 
Base Model(s)  Gemma 7B   google/gemma-7b
Model Size7b
Required VRAM17.1 GB
Updated2025-09-15
Maintainerwandb
Model Typegemma
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4
Model ArchitectureGemmaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.38.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemma 7B Zephyr Sft

Best Alternatives
Context / RAM
Downloads
Likes
Kaggle Math Model Gemma V112K / 17.1 GB50
Gemma 1.1 7B It8K / 17.1 GB13881274
SeaLLM 7B V2.58K / 17.1 GB1257250
Zephyr 7B Gemma DPO Avg8K / 17.1 GB150
Zephyr 7B Gemma Rpo Avg8K / 17.1 GB60
Zephyr 7B Gemma V0.18K / 17.1 GB1229123
... Codegemma 2 7B It Alpaca V1.38K / 17.1 GB61
... 7B Finetuned Sft Navarasa 2.08K / 34 GB129422
Codegemma 7B It8K / 17.1 GB6076231
Codegemma 7B8K / 17.1 GB5577201
Note: green Score (e.g. "73.2") means that the model is better than wandb/gemma-7b-zephyr-sft.

Rank the Gemma 7B Zephyr Sft 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? 51369 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 v20241124
  Support LLM Explorer