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 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Zephyr 7B Beta GPTQ   URL Share it on

  3968   
  Arxiv:2305.18290   Arxiv:2310.16944   4-bit   Autotrain compatible Base model:huggingfaceh4/zephy... Base model:quantized:huggingfa...   Conversational Dataset:huggingfaceh4/ultracha... Dataset:huggingfaceh4/ultrafee...   En   Generated from trainer   Gptq   Mistral   Quantized   Region:us   Safetensors

Zephyr 7B Beta GPTQ Benchmarks

LLME Score: 0.18858
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Zephyr 7B Beta GPTQ Parameters and Internals

Model Type 
GPT-like, fine-tuned
Use Cases 
Primary Use Cases:
chat-based applications, testing via demo
Limitations:
problematic outputs possible, educational and research use recommended
Considerations:
not aligned to human preferences with techniques like RLHF
Supported Languages 
en (primary)
Training Details 
Data Sources:
HuggingFaceH4/ultrachat_200k, HuggingFaceH4/ultrafeedback_binarized
Methodology:
Direct Preference Optimization
Hardware Used:
multi-GPU (16 devices)
Input Output 
Input Format:
<|system|> ~~ <|user|> {prompt}~~ <|assistant|>
LLM NameZephyr 7B Beta GPTQ
Repository 🤗https://huggingface.co/TheBloke/zephyr-7B-beta-GPTQ 
Model NameZephyr 7B Beta
Model CreatorHugging Face H4
Base Model(s)  Zephyr 7B Beta   HuggingFaceH4/zephyr-7b-beta
Model Size7b
Required VRAM4.2 GB
Updated2024-11-21
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16
Zephyr 7B Beta GPTQ (TheBloke/zephyr-7B-beta-GPTQ)

Quantized Models of the Zephyr 7B Beta GPTQ

Model
Likes
Downloads
VRAM
Zephyr Finetuned Legal1100 GB
Cesar Ptbr0190 GB

Best Alternatives to Zephyr 7B Beta GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB46032250
Mistral 7B Instruct V0.1 GPTQ32K / 4.2 GB113382577
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB74050
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB375215
Mistral 7B OpenOrca GPTQ32K / 4.2 GB442044100
...ephyr 7B Beta Channelwise Gptq32K / 4 GB134580
...hyr 7B Beta Channelwise Marlin32K / 4 GB67050
Zephyr 7B Beta Marlin32K / 4.1 GB68080
Dolphin 2.0 Mistral 7B GPTQ32K / 4.2 GB1190108
...istral 7B Pruned50 GPTQ Marlin32K / 4 GB100
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/zephyr-7B-beta-GPTQ.

Rank the Zephyr 7B Beta GPTQ 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? 38149 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 v20241110
  Support LLM Explorer