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

Mistral 7B Instruct V0.2 Bnb 4bit by unsloth

 »  All LLMs  »  unsloth  »  Mistral 7B Instruct V0.2 Bnb 4bit   URL Share it on

  14005   
  4-bit   4bit   Autotrain compatible   Bitsandbytes   Bnb   Conversational   En   Endpoints compatible   Instruct   Mistral   Mistral-7b   Mistral-instruct   Quantized   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit 

Mistral 7B Instruct V0.2 Bnb 4bit Benchmarks

MMLU Pro: 20.31
GPQA: 7.83
MUSR: 15.67
BBH: 11.15
IFEval: 46.34 vs 88 (so35)-47.3%
MATH Lvl 5: 1.44
LLME Score: 0.25864
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral 7B Instruct V0.2 Bnb 4bit (unsloth/mistral-7b-instruct-v0.2-bnb-4bit)

Mistral 7B Instruct V0.2 Bnb 4bit Parameters and Internals

Model Type 
text generation
Additional Notes 
Unsloth allows fine-tuning Mistral models 2-5 times faster with significant memory reduction.
Input Output 
Performance Tips:
Run on Google Colab with Tesla T4 for optimal performance.
LLM NameMistral 7B Instruct V0.2 Bnb 4bit
Repository 🤗https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit 
Base Model(s)  mistralai/mistral-7b-instruct-v0.2   mistralai/mistral-7b-instruct-v0.2
Model Size7b
Required VRAM4.1 GB
Updated2025-02-22
Maintainerunsloth
Model Typemistral
Instruction-BasedYes
Model Files  4.1 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Mistral 7B Instruct V0.2 Bnb 4bit

Model
Likes
Downloads
VRAM
Mistral 7B News Cnn Merged100 GB
...B Instruct V0.2 Bnb 4bit Tax 1022554 GB
Mistral Rank8 Sft01114 GB
Mistral Rank32 Sft0514 GB
Mistral Rank16 Sft0614 GB
Mistral Rank32 Invert0914 GB
Mistral Rank16 Invert0614 GB
Mistral Rank8 Invert01214 GB
Mistral7B MatheoAI8 Lora0514 GB
EMO Ai 7B1614 GB

Best Alternatives to Mistral 7B Instruct V0.2 Bnb 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...al Nemo Instruct 2407 Bnb 4bit1000K / 8.3 GB1885427
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB15850521
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB2701
MistralContinuedFine32K / 14.5 GB14470
NaturalLM 7B Instruct32K / 14.5 GB2110
Mistral 7B Instruct V0.2 8bit32K / 7.6 GB231
...eMistral 7B Instruct Ead 16bit32K / 14.5 GB380
Mistral Turkish V232K / 14.4 GB30396
...B Instruct V0.2 Bnb 4bit Tax 132K / 4.1 GB22550
Note: green Score (e.g. "73.2") means that the model is better than unsloth/mistral-7b-instruct-v0.2-bnb-4bit.

Rank the Mistral 7B Instruct V0.2 Bnb 4bit 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? 43470 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 v20241227
  Support LLM Explorer