Microsoft WizardLM 2 7B GPTQ by thesven

 ยป  All LLMs  ยป  thesven  ยป  Microsoft WizardLM 2 7B GPTQ   URL Share it on

  Arxiv:2304.12244   Arxiv:2306.08568   Arxiv:2308.09583   4-bit   Autotrain compatible   Conversational   Endpoints compatible   Gptq   Mistral   Quantized   Region:us   Safetensors

Microsoft WizardLM 2 7B GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Microsoft WizardLM 2 7B GPTQ (thesven/microsoft_WizardLM-2-7B-GPTQ)

Microsoft WizardLM 2 7B GPTQ Parameters and Internals

LLM NameMicrosoft WizardLM 2 7B GPTQ
Repository ๐Ÿค—https://huggingface.co/thesven/microsoft_WizardLM-2-7B-GPTQ 
Base Model(s)  Microsoft WizardLM 2 7B   lucyknada/microsoft_WizardLM-2-7B
Model Size7b
Required VRAM4.2 GB
Updated2024-12-23
Maintainerthesven
Model Typemistral
Model Files  4.2 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.42.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Microsoft WizardLM 2 7B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB55860950
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB150820
Mistral 7B Instruct V0.1 GPTQ32K / 4.2 GB15218878
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB151616
...ephyr 7B Beta Channelwise Gptq32K / 4 GB110630
...hyr 7B Beta Channelwise Marlin32K / 4 GB53900
Zephyr 7B Beta Marlin32K / 4.1 GB54560
...baraHermes 2.5 Mistral 7B GPTQ32K / 4.2 GB244855
...istral 7B Pruned50 GPTQ Marlin32K / 4 GB50
Mistral 7B Unsloth Gptq 8bit32K / 7.7 GB60
Note: green Score (e.g. "73.2") means that the model is better than thesven/microsoft_WizardLM-2-7B-GPTQ.

Rank the Microsoft WizardLM 2 7B GPTQ 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? 40126 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217