LongAlign 13B 64K GPTQ by MaziyarPanahi

 ยป  All LLMs  ยป  MaziyarPanahi  ยป  LongAlign 13B 64K GPTQ   URL Share it on

  Arxiv:2401.18058   4-bit   Autotrain compatible Base model:finetune:thudm/long... Base model:thudm/longalign-13b...   Dataset:thudm/longalign-10k   En   Endpoints compatible   Finetuned   Gptq   Llama   Long context   Pytorch   Quantized   Region:us   Safetensors   Zh

LongAlign 13B 64K GPTQ Benchmarks

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

LongAlign 13B 64K GPTQ Parameters and Internals

LLM NameLongAlign 13B 64K GPTQ
Repository ๐Ÿค—https://huggingface.co/MaziyarPanahi/LongAlign-13B-64k-GPTQ 
Model NameLongAlign-13B-64k-GPTQ
Model CreatorTHUDM
Base Model(s)  LongAlign 13B 64K   THUDM/LongAlign-13B-64k
Model Size13b
Required VRAM7.3 GB
Updated2024-09-07
MaintainerMaziyarPanahi
Model Typellama
Model Files  7.3 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length65536
Model Max Length65536
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32256
Torch Data Typefloat16
LongAlign 13B 64K GPTQ (MaziyarPanahi/LongAlign-13B-64k-GPTQ)

Best Alternatives to LongAlign 13B 64K GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB3216
...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

Rank the LongAlign 13B 64K 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