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 13B Fp16 by TheBloke

 »  All LLMs  »  TheBloke  »  Llama 2 13B Fp16   URL Share it on

  12302   
  Autotrain compatible   En   Facebook   Fp16   Llama   Llama2   Meta   Pytorch   Quantized   Region:us   Sharded

Llama 2 13B Fp16 Benchmarks

ARC: 60.41 vs 96.7 (so35)-37.5%
HellaSwag: 82.58 vs 95.3 (gpt4)-13.3%
MMLU: 55.86 vs 88.3 (so35)-36.7%
TruthfulQA: 43.61 vs 59 (gpt4)-26.1%
WinoGrande: 76.72 vs 87.5 (gpt4)-12.3%
GSM8K: 8.49 vs 96.4 (so35)-91.2%
LLME Score: 0.21585
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama 2 13B Fp16 Parameters and Internals

LLM NameLlama 2 13B Fp16
Repository 🤗https://huggingface.co/TheBloke/Llama-2-13B-fp16 
Base Model(s)  Ligma L2 13B   kubernetes-bad/Ligma-L2-13b
Model Size13b
Required VRAM26 GB
Updated2024-09-19
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.30.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16
Llama 2 13B Fp16 (TheBloke/Llama-2-13B-fp16)

Quantized Models of the Llama 2 13B Fp16

Model
Likes
Downloads
VRAM
LLaMA2 13B Estopia189226 GB
...MA2 13B Estopia 8.0bpw H8 EXL21513 GB
...MA2 13B Estopia 3.0bpw H6 EXL2155 GB
Storytelling V2 13B Lora710 GB
Lmg V3 Lora200 GB
Storytelling V1 13B Lora630 GB
Minotaur Llama2 13B Qlora431 GB

Best Alternatives to Llama 2 13B Fp16

Best Alternatives
Context / RAM
Downloads
Likes
...Maid V3 13B 32K 6.0bpw H6 EXL232K / 10 GB61
...Maid V3 13B 32K 8.0bpw H8 EXL232K / 13.2 GB41
WhiteRabbitNeo 13B V116K / 26 GB1464380
CodeLlama 13B Python Fp1616K / 26 GB144425
CodeLlama 13B Instruct Fp1616K / 26 GB145329
Codellama 13B Bnb 4bit16K / 7.2 GB1071
CodeLlama 13B Fp1616K / 26 GB1666
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB82
Trinity 13B16K / 26 GB515
WhiteRabbitNeo 13B V1 4bit Mlx16K / 7.8 GB01
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-13B-fp16.

Rank the Llama 2 13B Fp16 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? 36030 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