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

Zephyr 7B Beta 5.0bpw EXL2 by mlabonne

 »  All LLMs  »  mlabonne  »  Zephyr 7B Beta 5.0bpw EXL2   URL Share it on

  18   
  Arxiv:2305.18290   Arxiv:2310.16944   Autotrain compatible Base model:mistralai/mistral-7...   Conversational Dataset:huggingfaceh4/ultracha... Dataset:huggingfaceh4/ultrafee...   En   Endpoints compatible   Exl2   Generated from trainer   License:mit   Mistral   Quantized   Region:us   Safetensors

Zephyr 7B Beta 5.0bpw EXL2 Benchmarks

HF Avg Score: 60.1  vs  86.1  (GPT-4) -30.2%
ARC: 73.6-23.6%
HellaSwag: 66.3-30.4%
MMLU: 56.4-34.8%
GSM8K: 34.2-62.8%
OpenCompass Avg: 53.6  vs  73.3  (GPT-4) -26.9%
Exam: 63.7-17.5%
Language: 41.9-32.4%
Knowledge: 58.1-21%
Understanding: 62.3-11%
Reasoning: 49.8-33.1%
nn.n% — How the model compares to the GPT-4.

Rank the Zephyr 7B Beta 5.0bpw 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  
Zephyr 7B Beta 5.0bpw EXL2 (mlabonne/zephyr-7b-beta-5.0bpw-exl2)

Best Alternatives to Zephyr 7B Beta 5.0bpw EXL2

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
KAI 7B V0.174.4532K / 14.4 GB1410
Dolphin 2.2.1 Mistral 7B73.1732K / 14.4 GB8003188
Mistral 7B V0.168.5332K / 14.4 GB7103103291
....1 Mistral 7B Bnb 4bit Smashed64.232K / 4.5 GB140
....1 Mistral 7B AWQ 4bit Smashed64.232K / 4.2 GB80
...andle Dolphin 2.2.1 Mistral 7B64.232K / 14.4 GB2650
Mistral 7B Instruct V0.162.2332K / 14.4 GB4013861465
Notus 7B V160.1532K / 14.4 GB3474118
...t 3.5 0106 128K 4.0bpw H6 EXL260.1128K / 3.9 GB01
...t 3.5 0106 128K 8.0bpw H8 EXL260.1128K / 7.4 GB01
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/zephyr-7b-beta-5.0bpw-exl2.

Zephyr 7B Beta 5.0bpw EXL2 Parameters and Internals

LLM NameZephyr 7B Beta 5.0bpw EXL2
RepositoryOpen on 🤗 
Base Model(s)  Mistral 7B V0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM0 GB
Updated2024-07-05
Maintainermlabonne
Model Typemistral
Model Files  0.0 GB   1.7 GB   4.7 GB   0.0 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.35.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 34431 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 v2024042801
  Support LLM Explorer