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

Selfrag Zh Baichuan2 7B Chat by Aman

 »  All LLMs  »  Aman  »  Selfrag Zh Baichuan2 7B Chat   URL Share it on

  8   

Selfrag Zh Baichuan2 7B Chat is an open-source language model by Aman. Features: 7b LLM, VRAM: 15GB, Context: 4K, License: mit, LLM Explorer Score: 0.12.

  Baichuan   Baichuan2   Custom code   Endpoints compatible   Pytorch   Rag   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Aman/selfrag-zh_baichuan2_7b_chat 

Selfrag Zh Baichuan2 7b Chat Benchmarks

LLME Score: 0.12091
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Selfrag Zh Baichuan2 7B Chat (Aman/selfrag-zh_baichuan2_7b_chat)
🌟 Advertise your project 🚀

Selfrag Zh Baichuan2 7B Chat Parameters and Internals

Model Type 
Text Generation, RAG
Additional Notes 
The model aligns reflection tokens with the English original, and includes a 'critic model' that requires further refinement based on critic data quality.
Supported Languages 
Chinese (High proficiency)
Training Details 
Data Sources:
belle SFT data, Wikipedia Chinese docs
Data Volume:
4w.jsonl
Methodology:
Self-RAG based training
Model Architecture:
7B parameter model architecture
Input Output 
Input Format:
Text prompts with optional retrieval-enhanced input
Accepted Modalities:
Text
Output Format:
Text sequences
Performance Tips:
Use original generate method of transformers for best accuracy
LLM NameSelfrag Zh Baichuan2 7b Chat
Repository 🤗https://huggingface.co/Aman/selfrag-zh_baichuan2_7b_chat 
Model Size7b
Required VRAM15 GB
Updated2026-04-04
MaintainerAman
Model Typebaichuan
Model Files  9.9 GB: 1-of-2   5.1 GB: 2-of-2
Model ArchitectureBaichuanForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.33.0
Tokenizer ClassBaichuanTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size125711
Torch Data Typebfloat16

Best Alternatives to Selfrag Zh Baichuan2 7B Chat

Best Alternatives
Context / RAM
Downloads
Likes
Baichuan2 7B PoSE YaRN 16K16K / 15 GB71
Baichuan2 7B PoSE Linear 16K16K / 15 GB21
Baichuan2 7B PoSE NTK 16K16K / 15 GB11
Baichuan2 7B Chat4K / 15 GB80961171
DocLLM Baichuan2 7b4K / 18.3 GB65
HuatuoGPT2 7B4K / 15 GB109810
Baichuan2 7B Base4K / 15 GB179186
Blossom V4 Baichuan2 7B4K / 15 GB51
HuatuoGPT2 7B 4bits4K / 5.4 GB234
HuatuoGPT2 7B 8bits4K / 8.7 GB122
Note: green Score (e.g. "73.2") means that the model is better than Aman/selfrag-zh_baichuan2_7b_chat.

Rank the Selfrag Zh Baichuan2 7B Chat 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer