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 by togethercomputer

 »  All LLMs  »  togethercomputer  »  LLaMA 2 7B 32K   URL Share it on

  5657   
  Autotrain compatible   Dataset:eleutherai/pile Dataset:togethercomputer/long-... Dataset:togethercomputer/redpa... Dataset:togethercomputer/redpa...   En   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/togethercomputer/LLaMA-2-7B-32K 

LLaMA 2 7B 32K Benchmarks

MMLU Pro: 8.53
MUSR: 4.32
BBH: 8.09
IFEval: 18.65 vs 88 (so35)-78.8%
ARC: 47.53 vs 96.7 (so35)-50.8%
HellaSwag: 76.14 vs 95.3 (gpt4)-20.1%
MMLU: 43.33 vs 88.3 (so35)-50.9%
TruthfulQA: 39.23 vs 59 (gpt4)-33.5%
WinoGrande: 71.9 vs 87.5 (gpt4)-17.8%
GSM8K: 4.32 vs 96.4 (so35)-95.5%
MATH Lvl 5: 1.44
LLME Score: 0.22182
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 (togethercomputer/LLaMA-2-7B-32K)

LLaMA 2 7B 32K Parameters and Internals

Model Type 
long context language model
Additional Notes 
Model can be fine-tuned on specific applications using OpenChatKit.
Supported Languages 
en (English)
Training Details 
Data Sources:
togethercomputer/RedPajama-Data-1T, togethercomputer/RedPajama-Data-Instruct, EleutherAI/pile, togethercomputer/Long-Data-Collections
Methodology:
Follows Llama-2-7B's architecture using a mixture of pre-training and instruction tuning data.
Context Length:
32000
Model Architecture:
Extends original Llama-2-7B to handle a longer context with optimizations like FlashAttention-2.
Input Output 
Accepted Modalities:
text
Performance Tips:
Install Flash Attention V2 for optimal performance.
LLM NameLLaMA 2 7B 32K
Repository 🤗https://huggingface.co/togethercomputer/LLaMA-2-7B-32K 
Model Size7b
Required VRAM13.5 GB
Updated2025-05-14
Maintainertogethercomputer
Model Typellama
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length32768
Model Max Length32768
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to LLaMA 2 7B 32K

Best Alternatives
Context / RAM
Downloads
Likes
A6 L1024K / 16.1 GB2010
M1024K / 16.1 GB1270
1571024K / 16.1 GB1010
1241024K / 16.1 GB930
A3.41024K / 16.1 GB130
A5.41024K / 16.1 GB120
A2.41024K / 16.1 GB120
2 Very Sci Fi1024K / 16.1 GB3170
1621024K / 16.1 GB600
1181024K / 16.1 GB150
Note: green Score (e.g. "73.2") means that the model is better than togethercomputer/LLaMA-2-7B-32K.

Rank the LLaMA 2 7B 32K 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? 47340 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