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 32K Instruct AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Llama 2 7B 32K Instruct AWQ   URL Share it on

  10   
  Arxiv:2307.03172   4-bit   Autotrain compatible   Awq Base model:quantized:togetherc... Base model:togethercomputer/ll...   Custom code Dataset:togethercomputer/llama...   En   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-AWQ 

Llama 2 7B 32K Instruct AWQ Benchmarks

LLME Score: 0.10681
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 32K Instruct AWQ (TheBloke/Llama-2-7B-32K-Instruct-AWQ)
🌟 Advertise your project 🚀

Llama 2 7B 32K Instruct AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Model is optimized using AWQ (Efficient, accurate low-bit weight quantization).
Training Details 
Data Sources:
togethercomputer/llama-instruct, BookSum dataset, Multi-document Question Answering
Data Volume:
19K instruction + BookSum (25%) + MQA (25%)
Methodology:
finetuned over high-quality instruction and chat data
Input Output 
Input Format:
[INST] {prompt} [/INST]
Accepted Modalities:
text
Output Format:
text
LLM NameLlama 2 7B 32K Instruct AWQ
Repository 🤗https://huggingface.co/TheBloke/Llama-2-7B-32K-Instruct-AWQ 
Model NameLlama2 7B 32K Instruct
Model CreatorTogether
Base Model(s)  Llama 2 7B 32K Instruct   togethercomputer/Llama-2-7B-32K-Instruct
Model Size7b
Required VRAM3.9 GB
Updated2025-09-23
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  3.9 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length32768
Model Max Length32768
Transformers Version4.31.0
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 32K Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 7B Instruct AWQ16K / 3.9 GB12794
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB61
...ama 7B Instruct Hf W4 G128 AWQ16K / 3.9 GB60
CausalLM 7B AWQ8K / 5.8 GB133
...essianai 7B Chat Bilingual AWQ8K / 3.9 GB152
Leo Hessianai 7B Chat AWQ8K / 3.9 GB61
...epseek Math 7B Instruct AWQ Q44K / 4.8 GB130
Llama 2 7B Ft Instruct Es AWQ4K / 3.9 GB61
Swallow 7B Instruct AWQ4K / 4.1 GB91
...i 7B Sft Qa Context Jaqket AWQ4K / 3.9 GB61
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-7B-32K-Instruct-AWQ.

Rank the Llama 2 7B 32K Instruct 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? 51545 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