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

Xgen 7B 8K Open Instruct Gptq by SearchUnify-ML

 »  All LLMs  »  SearchUnify-ML  »  Xgen 7B 8K Open Instruct Gptq   URL Share it on

  12   
  4bit   Autotrain compatible Dataset:vmware/open-instruct-v...   En   Ext 8k   Gptq   Instruct   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/SearchUnify-ML/xgen-7b-8k-open-instruct-gptq 

Xgen 7B 8K Open Instruct Gptq Benchmarks

LLME Score: 0.12005
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Xgen 7B 8K Open Instruct Gptq (SearchUnify-ML/xgen-7b-8k-open-instruct-gptq)

Xgen 7B 8K Open Instruct Gptq Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
text generation, cognitive search, support, self-service
Applications:
Cognitive Search, SUVA, Knowbler, Escalation Predictor, Agent Helper, Community Helper
Primary Use Cases:
Deliver accurate and contextually appropriate support and self-service experiences
Additional Notes 
This model utilizes GPTQ quantization method for a low memory footprint.
Training Details 
Data Sources:
VMware/open-instruct-v1-oasst-dolly-hhrlhf
Methodology:
Quantized to 4bit using GPTQ-for-LLaMa
Context Length:
8000
Model Architecture:
GPTQ 4bit
LLM NameXgen 7B 8K Open Instruct Gptq
Repository 🤗https://huggingface.co/SearchUnify-ML/xgen-7b-8k-open-instruct-gptq 
Base Model(s)  Xgen 7B 8K Open Instruct   VMware/xgen-7b-8k-open-instruct
Model Size7b
Required VRAM4.2 GB
Updated2024-12-22
MaintainerSearchUnify-ML
Model Typellama
Instruction-BasedYes
Model Files  4.2 GB
Supported Languagesen
GPTQ QuantizationYes
Context Length8k
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licensecc
Context Length8192
Model Max Length8192
Transformers Version4.28.0
Tokenizer ClassXgenTokenizer
End of Sentence Token<|endoftext|>
Vocabulary Size51200
Torch Data Typefloat16

Best Alternatives to Xgen 7B 8K Open Instruct Gptq

Best Alternatives
Context / RAM
Downloads
Likes
... 7B 32K Instructions V4 Marlin32K / 4.1 GB120
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB7227
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB360
CodeLlama 7B Instruct GPTQ16K / 3.9 GB55046
...echless Tora Code 7B V1.0 GPTQ16K / 3.9 GB191
CausalLM 7B GPTQ8K / 5.9 GB595
Leo Hessianai 7B Chat GPTQ8K / 3.9 GB570
...ssianai 7B Chat Bilingual GPTQ8K / 3.9 GB240
Deepseek Math 7B Instruct GPTQ4K / 4.8 GB170
... Qa Context Jaqket Jsquad Gptq4K / 3.9 GB80
Note: green Score (e.g. "73.2") means that the model is better than SearchUnify-ML/xgen-7b-8k-open-instruct-gptq.

Rank the Xgen 7B 8K Open Instruct Gptq 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? 40066 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 v20241217
  Support LLM Explorer