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

XuanYuan 70B Chat 8bit by Duxiaoman-DI

 »  All LLMs  »  Duxiaoman-DI  »  XuanYuan 70B Chat 8bit   URL Share it on

  19   
  8-bit   8bit   Autotrain compatible   Bitsandbytes   Endpoints compatible   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Duxiaoman-DI/XuanYuan-70B-Chat-8bit 

XuanYuan 70B Chat 8bit Benchmarks

LLME Score: 0.11695
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
XuanYuan 70B Chat 8bit (Duxiaoman-DI/XuanYuan-70B-Chat-8bit)
🌟 Advertise your project 🚀

XuanYuan 70B Chat 8bit Parameters and Internals

Model Type 
Text Generation, Financial Analysis
Use Cases 
Areas:
Finance, General text processing
Applications:
Financial analysis, General AI chatbot applications
Primary Use Cases:
Answering financial questions, Engaging in general conversations
Limitations:
May not perform well beyond financial and general use scopes.
Considerations:
General chatbot ethics and data privacy should be considered.
Additional Notes 
The XuanYuan model series is specifically optimized for financial texts while maintaining a broad applicability to general language processing tasks.
Supported Languages 
Chinese (High), English (High)
Training Details 
Data Sources:
General web sources, Financial news, Company announcements, Financial books, Certification exam questions
Methodology:
Incremental pre-training with both general and financial-specific data. Enhanced vocabulary to maintain English proficiency and improve Chinese understanding.
Context Length:
8192
Hardware Used:
100x GPU Cluster with 8x A800 (80G) per node
Model Architecture:
Enhanced version of Llama2 architecture, optimized for distributed training and extended context handling.
Input Output 
Input Format:
Usual NLP input formats, token-based input for extended context processing.
Accepted Modalities:
Text
Output Format:
NLP text output.
Performance Tips:
For optimal performance, ensure adequate GPU memory and adhere to training methodologies when further tuning.
LLM NameXuanYuan 70B Chat 8bit
Repository 🤗https://huggingface.co/Duxiaoman-DI/XuanYuan-70B-Chat-8bit 
Base Model(s)  XuanYuan 70B Chat   Duxiaoman-DI/XuanYuan-70B-Chat
Model Size70b
Required VRAM69.8 GB
Updated2025-09-23
MaintainerDuxiaoman-DI
Model Typellama
Model Files  9.8 GB: 1-of-8   9.8 GB: 2-of-8   9.9 GB: 3-of-8   9.8 GB: 4-of-8   9.9 GB: 5-of-8   9.8 GB: 6-of-8   9.9 GB: 7-of-8   0.9 GB: 8-of-8
Quantization Type8bit
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length8192
Model Max Length8192
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size39438
Torch Data Typefloat16

Best Alternatives to XuanYuan 70B Chat 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB185
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB63
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB122
...0B Instruct Gradient 262K 4bit256K / 39.7 GB103
...0B Instruct Gradient 262K 8bit256K / 75 GB52
...0B Instruct Gradient 262K 2bit256K / 21.9 GB91
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB80
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB51
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB60
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than Duxiaoman-DI/XuanYuan-70B-Chat-8bit.

Rank the XuanYuan 70B Chat 8bit 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? 51535 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