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

  5031   
  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: 0.24053
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ft Mistral 7B Instruct V0.2 Sorry Bench 202406 (sorry-bench/ft-mistral-7b-instruct-v0.2-sorry-bench-202406)

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
Updated2025-02-05
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

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

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB760
...1 Summarize 64K LoRANET Merged128K / 14.4 GB50
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB12462781551
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37145
...ty Instruct 3M 0613 Mistral 7B32K / 14.4 GB641511
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? 42577 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