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 Chat AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Llama 2 7B Chat AWQ   URL Share it on

  7652   
  Arxiv:2307.09288   4-bit   Autotrain compatible   Awq Base model:meta-llama/llama-2-... Base model:quantized:meta-llam...   En   Facebook   Llama   Llama2   Meta   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-7B-Chat-AWQ 

Llama 2 7B Chat AWQ Benchmarks

LLME Score: 0.16825
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 Chat AWQ (TheBloke/Llama-2-7B-Chat-AWQ)

Llama 2 7B Chat AWQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Commercial applications, Research
Applications:
Assistant-like chat, Natural language generation
Primary Use Cases:
Dialogue optimization, Prompt-based text generation
Limitations:
English only, Not suitable for illegal uses
Considerations:
Developers should adhere to licensing agreements and perform additional safety testing.
Additional Notes 
Model achieved lower emissions with Meta's sustainability program.
Supported Languages 
en (High proficiency)
Training Details 
Data Sources:
A new mix of publicly available online data
Data Volume:
2 trillion tokens
Methodology:
Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:
4096
Training Time:
Between January 2023 and July 2023
Hardware Used:
A100-80GB GPUs
Model Architecture:
Transformer architecture
Safety Evaluation 
Methodologies:
Internal evaluations
Findings:
Fine-tuned Llama-2-Chat models have 0% Toxigen
Risk Categories:
Misinformation, Bias
Ethical Considerations:
This model may produce inaccurate, biased or objectionable responses.
Responsible Ai Considerations 
Fairness:
Conducted safe testing in English.
Transparency:
Usage requires adherence to licensing agreements.
Accountability:
Meta is accountable for the open release.
Mitigation Strategies:
Recommendations for developers to perform safety testing and tuning tailored to specific applications.
Input Output 
Input Format:
[INST] <> {prompt} [/INST]
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Avoid non-factual or biased prompts for safety and accuracy.
Release Notes 
Version:
V1
Date:
July 2023
Notes:
Initial release with enhanced safety and performance benchmarks.
LLM NameLlama 2 7B Chat AWQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-7B-Chat-AWQ 
Model NameLlama 2 7B Chat
Model CreatorMeta Llama 2
Base Model(s)  Llama 2 7B Chat Hf   meta-llama/Llama-2-7b-chat-hf
Model Size7b
Required VRAM3.9 GB
Updated2025-03-04
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
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 Typefloat16

Best Alternatives to Llama 2 7B Chat AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 AWQ195K / 19.3 GB91
Yarn Llama 2 7B 64K AWQ64K / 3.9 GB1180
Calm2 7B Chat AWQ32K / 4.4 GB1132
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB1212
... SWE Llama 7B Updated 4bit AWQ16K / 3.9 GB820
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB33120
CodeLlama 7B Instruct AWQ16K / 3.9 GB14234
Pandalyst 7B V1.2 AWQ16K / 3.9 GB831
Tora Code 7B V1.0 AWQ16K / 3.9 GB770
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB821
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-7B-Chat-AWQ.

Rank the Llama 2 7B Chat AWQ 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? 44202 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 v20241227
  Support LLM Explorer