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 70B Hf by meta-llama

 »  All LLMs  »  meta-llama  »  Llama 2 70B Hf   URL Share it on

  63585   
  Arxiv:2307.09288   Autotrain compatible   En   Endpoints compatible   Facebook   License:llama2   Llama   Llama2   Meta   Pytorch   Region:us   Safetensors   Sharded   Tensorflow

Llama 2 70B Hf Benchmarks

MMLU Pro: 30.2
GPQA: 7.05
MUSR: 9.78
BBH: 35.9
IFEval: 24.07 vs 88 (so35)-72.6%
ARC: 67.32 vs 96.7 (so35)-30.4%
HellaSwag: 87.33 vs 95.3 (gpt4)-8.4%
MMLU: 69.83 vs 88.3 (so35)-20.9%
TruthfulQA: 44.92 vs 59 (gpt4)-23.9%
WinoGrande: 83.74 vs 87.5 (gpt4)-4.3%
GSM8K: 54.06 vs 96.4 (so35)-43.9%
MATH Lvl 5: 2.49
LLME Score: 0.33039
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama 2 70B Hf Parameters and Internals

LLM NameLlama 2 70B Hf
Repository 🤗https://huggingface.co/meta-llama/Llama-2-70b-hf 
Model Size70b
Required VRAM138 GB
Updated2024-07-15
Maintainermeta-llama
Model Typellama
Model Files  9.8 GB: 1-of-15   9.8 GB: 2-of-15   10.0 GB: 3-of-15   9.8 GB: 4-of-15   9.8 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   9.8 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.5 GB: 14-of-15   0.5 GB: 15-of-15   9.8 GB: 1-of-15   9.8 GB: 2-of-15   10.0 GB: 3-of-15   9.8 GB: 4-of-15   9.8 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   9.8 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.5 GB: 14-of-15   0.5 GB: 15-of-15
Supported Languagesen
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
Llama 2 70B Hf (meta-llama/Llama-2-70b-hf)

Quantized Models of the Llama 2 70B Hf

Model
Likes
Downloads
VRAM
Llama 2 70B AWQ14211436 GB
Llama 2 70B GGUF29149029 GB
Tulu 2 DPO 70B 4.0bpw H6 EXL21835 GB
Tulu 2 70B 6.0bpw H6 EXL21552 GB
Tulu 2 DPO 70B 5.0bpw H6 EXL22743 GB
Tulu 2 DPO 70B 2.4bpw H6 EXL21621 GB
Llama 2 70B GPTQ83199235 GB

Best Alternatives to Llama 2 70B Hf

Best Alternatives
Context / RAM
Downloads
Likes
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB1126118
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB32395
Llama3 Function Calling 1048K1024K / 141.9 GB11
...a 3 70B Instruct Gradient 524K512K / 141.9 GB16123
...a 3 70B Instruct Gradient 262K256K / 141.9 GB18855
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB1463
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB1442
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB910
Yi 70B 200K RPMerge Franken195K / 142.4 GB21
Meta Llama 3.1 70B Instruct128K / 141.9 GB452826480
Note: green Score (e.g. "73.2") means that the model is better than meta-llama/Llama-2-70b-hf.

Rank the Llama 2 70B Hf 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? 35941 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 v2024072803
  Support LLM Explorer