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

Ft Mistral 7B Instruct V0.2 Sorry Bench 202406 by sorry-bench

 »  All LLMs  »  sorry-bench  »  Ft Mistral 7B Instruct V0.2 Sorry Bench 202406   URL Share it on

  372   
  Arxiv:2406.14598   Autotrain compatible   Benchmark   Conversational Dataset:sorry-bench/sorry-benc... Dataset:sorry-bench/sorry-benc...   En   Endpoints compatible   Evaluation   Instruct   Mistral   Region:us   Safetensors   Safety   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/sorry-bench/ft-mistral-7b-instruct-v0.2-sorry-bench-202406 

Ft Mistral 7B Instruct V0.2 Sorry Bench 202406 Benchmarks

LLME Score: 0.18565
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Ft Mistral 7B Instruct V0.2 Sorry Bench 202406 Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research, Benchmarking Safety Behaviors
Primary Use Cases:
Safety refusal judge for SORRY-Bench
Limitations:
Not meant for general-purpose safeguarding in LLM conversations
Additional Notes 
Only trained on human judgments of model responses to SORRY-Bench data.
Supported Languages 
en (High)
Training Details 
Data Sources:
SORRY-Bench Human Judgment Dataset
Methodology:
Fine-tuning
Hardware Used:
A100 GPU
Input Output 
Input Format:
Prompts with User Request and Model Response structure
Accepted Modalities:
text
Output Format:
Binary output 0 or 1
Performance Tips:
Use correct prompt template and formatting as specified in Mistral-7B-Instruct-v0.2
LLM NameFt Mistral 7B Instruct V0.2 Sorry Bench 202406
Repository 🤗https://huggingface.co/sorry-bench/ft-mistral-7b-instruct-v0.2-sorry-bench-202406 
Model Size7b
Required VRAM28.9 GB
Updated2025-04-15
Maintainersorry-bench
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-6   4.9 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   4.8 GB: 5-of-6   4.2 GB: 6-of-6
Supported Languagesen
Gated ModelYes
Model ArchitectureMistralForCausalLM
Licenseproprietary
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat32
Ft Mistral 7B Instruct V0.2 Sorry Bench 202406 (sorry-bench/ft-mistral-7b-instruct-v0.2-sorry-bench-202406)

Best Alternatives to Ft Mistral 7B Instruct V0.2 Sorry Bench 202406

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB168216
SpydazWeb AI HumanAI RP512K / 14.4 GB161
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB100
...1 Summarize 64K LoRANET Merged128K / 14.4 GB200
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB2531581710
Mixtral AI CyberCoder32K / 14.3 GB00
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB15745
Note: green Score (e.g. "73.2") means that the model is better than sorry-bench/ft-mistral-7b-instruct-v0.2-sorry-bench-202406.

Rank the Ft Mistral 7B Instruct V0.2 Sorry Bench 202406 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? 48023 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