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

Llama 2 7B Sharded by Xilabs

 »  All LLMs  »  Xilabs  »  Llama 2 7B Sharded   URL Share it on

  7   
  Arxiv:2307.09288   Autotrain compatible   En   Facebook   Llama   Llama2   Meta   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Xilabs/Llama-2-7b-Sharded 

Llama 2 7B Sharded Benchmarks

LLME Score: 0.09624
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B Sharded (Xilabs/Llama-2-7b-Sharded)
🌟 Advertise your project 🚀

Llama 2 7B Sharded Parameters and Internals

Model Type 
text generation, language model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Assistant-like chat, Natural language generation
Primary Use Cases:
Assistant-like chat, Instruction following, Natural language tasks
Limitations:
May produce biased or objectionable content, Limited to English language
Considerations:
Developers should verify outputs prior to deployment.
Additional Notes 
Future versions may be released for improved safety.
Supported Languages 
en (High Proficiency)
Training Details 
Data Sources:
publicly available online data, instruction datasets
Data Volume:
2 trillion tokens
Methodology:
auto-regressive transformer with SFT and RLHF
Context Length:
4000
Training Time:
January 2023 to July 2023
Hardware Used:
Meta's Research Super Cluster, production clusters of third-party cloud compute
Model Architecture:
optimized transformer
Safety Evaluation 
Methodologies:
internal evaluations library, TruthfulQA, Toxigen
Findings:
Llama 2 70B achieves higher scores across benchmarks compared to other versions, lower toxicity in Llama-2-Chat versions
Risk Categories:
misinformation, bias
Ethical Considerations:
ensuring outputs are not objectionable and testing before deployment
Responsible Ai Considerations 
Fairness:
Testing conducted in English; potential biases need addressing.
Transparency:
Open publication of training details and carbon footprint.
Accountability:
Developers should test and tune model implementations.
Mitigation Strategies:
SFT and RLHF used in tuning; Responsible Use Guide provided.
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
Performance Tips:
For chat versions, use specific formatting including 'INST' tags.
LLM NameLlama 2 7B Sharded
Repository 🤗https://huggingface.co/Xilabs/Llama-2-7b-Sharded 
Model Size7b
Required VRAM13.4 GB
Updated2025-09-23
MaintainerXilabs
Model Typellama
Model Files  0.6 GB: 1-of-23   0.6 GB: 2-of-23   0.6 GB: 3-of-23   0.6 GB: 4-of-23   0.6 GB: 5-of-23   0.6 GB: 6-of-23   0.6 GB: 7-of-23   0.6 GB: 8-of-23   0.6 GB: 9-of-23   0.6 GB: 10-of-23   0.6 GB: 11-of-23   0.6 GB: 12-of-23   0.6 GB: 13-of-23   0.6 GB: 14-of-23   0.6 GB: 15-of-23   0.6 GB: 16-of-23   0.6 GB: 17-of-23   0.6 GB: 18-of-23   0.6 GB: 19-of-23   0.6 GB: 20-of-23   0.6 GB: 21-of-23   0.5 GB: 22-of-23   0.3 GB: 23-of-23
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Llama 2 7B Sharded

Model
Likes
Downloads
VRAM
Llama 2 7B Bf16 Sharded74168613 GB

Best Alternatives to Llama 2 7B Sharded

Best Alternatives
Context / RAM
Downloads
Likes
A6 L1024K / 16.1 GB2010
A3.41024K / 16.1 GB130
A5.41024K / 16.1 GB120
A2.41024K / 16.1 GB120
M1024K / 16.1 GB1270
1571024K / 16.1 GB1010
1241024K / 16.1 GB930
1621024K / 16.1 GB600
2 Very Sci Fi1024K / 16.1 GB3170
1181024K / 16.1 GB150
Note: green Score (e.g. "73.2") means that the model is better than Xilabs/Llama-2-7b-Sharded.

Rank the Llama 2 7B Sharded 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? 51547 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