Yarn Llama 2 13B 128K GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Yarn Llama 2 13B 128K GPTQ   URL Share it on

  Arxiv:2309.00071   4-bit   Autotrain compatible Base model:nousresearch/yarn-l... Base model:quantized:nousresea...   Custom code   Dataset:pg19   Gptq   Llama   Quantized   Region:us   Safetensors   Yarn

Yarn Llama 2 13B 128K GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Yarn Llama 2 13B 128K GPTQ Parameters and Internals

LLM NameYarn Llama 2 13B 128K GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Yarn-Llama-2-13B-128K-GPTQ 
Model NameYarn Llama 2 13B 128K
Model CreatorNousResearch
Base Model(s)  Yarn Llama 2 13B 128K   NousResearch/Yarn-Llama-2-13b-128k
Model Size13b
Required VRAM7.3 GB
Updated2024-09-07
MaintainerTheBloke
Model Typellama
Model Files  7.3 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length131072
Model Max Length131072
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16
Yarn Llama 2 13B 128K GPTQ (TheBloke/Yarn-Llama-2-13B-128K-GPTQ)

Best Alternatives to Yarn Llama 2 13B 128K GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
LongAlign 13B 64K GPTQ64K / 7.3 GB171
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB153
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB171
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB173
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB84
EverythingLM 13B 16K GPTQ16K / 7.3 GB2913
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB81
Tinybra 13B GPTQ 4BIT16K / 7 GB80
WhiteRabbitNeo 13B GPTQ16K / 7.3 GB134
NexusRaven V2 13B GPTQ16K / 7.3 GB423
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Yarn-Llama-2-13B-128K-GPTQ.

Rank the Yarn Llama 2 13B 128K GPTQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803