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 V0.3 Chinese Chat 4bit by shenzhi-wang

 »  All LLMs  »  shenzhi-wang  »  Mistral 7B V0.3 Chinese Chat 4bit   URL Share it on

  227   
  Arxiv:2403.07691   4bit   Autotrain compatible Base model:mistralai/mistral-7... Base model:quantized:mistralai...   Conversational   En   Endpoints compatible   Gguf   Instruct   Llama-factory   Mistral   Orpo   Q4   Quantized   Region:us   Zh

Mistral 7B V0.3 Chinese Chat 4bit Benchmarks

LLME Score: 0.21531
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Mistral 7B V0.3 Chinese Chat 4bit Parameters and Internals

Model Type 
text generation, instruction-tuned
Use Cases 
Areas:
Chinese and English user applications
Applications:
roleplaying, tool use, mathematics
Primary Use Cases:
text generation in Chinese and English, chat and instruction following
Additional Notes 
The model significantly improves Chinese language capabilities compared to its base model. Uses meticulously fine-tuned ORPO methodology to handle multilingual interactions efficiently.
Supported Languages 
en (fluent), zh (fluent)
Training Details 
Data Sources:
Chinese-English dataset of ~100K preference pairs
Data Volume:
~100K preference pairs
Methodology:
Full-parameter fine-tuning using ORPO
Context Length:
32768
Model Architecture:
Built on Mistral-7B-Instruct-v0.3
Input Output 
Input Format:
Text input in form of user-system interaction
Accepted Modalities:
text
Output Format:
Textual responses, including roleplaying and conversation prompts
Performance Tips:
Avoid identity-related questions as they may yield random responses
Release Notes 
Version:
v0.3
Date:
May 26, 2024
Notes:
First model fine-tuned for Chinese and English users based on Mistral-7B-Instruct-v0.3
LLM NameMistral 7B V0.3 Chinese Chat 4bit
Repository 🤗https://huggingface.co/shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat-4bit 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.3   mistralai/Mistral-7B-Instruct-v0.3
Model Size7b
Required VRAM4.1 GB
Updated2024-11-21
Maintainershenzhi-wang
Model Typemistral
Instruction-BasedYes
Model Files  4.1 GB
Supported Languagesen zh
GGUF QuantizationYes
Quantization Typegguf|q4|4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.40.0
Vocabulary Size32768
Torch Data Typebfloat16
Mistral 7B V0.3 Chinese Chat 4bit (shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat-4bit)

Best Alternatives to Mistral 7B V0.3 Chinese Chat 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2.gguf32K / 14.5 GB103
Mistral 7B Instruct V0.2 GGUF32K / 4.4 GB532
...andle Mistral 7B Instruct V0.232K / 14.4 GB410
BioMistralMerged32K / 14.4 GB39030
Tamil Mistral 7B Instruct V0.132K / 14.8 GB55113
...stral 7B V0.3 Chinese Chat F1632K / 14.5 GB6341
Mistral 7B Instruct V0.3 GGUF32K / 2.7 GB930
Mistral 7B Instruct V0.3 GGUF32K / 2.7 GB490
...tral 7B V0.3 Chinese Chat 8bit32K / 7.7 GB163
...7B Instruct V0.2 SFT Local 27632K / 14.4 GB80
Note: green Score (e.g. "73.2") means that the model is better than shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat-4bit.

Rank the Mistral 7B V0.3 Chinese Chat 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? 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