BigTranslate 13B GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  BigTranslate 13B GPTQ   URL Share it on

  Arxiv:2305.18098   4-bit   Autotrain compatible   Gptq   Llama   Quantized   Region:us   Safetensors

BigTranslate 13B GPTQ Benchmarks

BigTranslate 13B GPTQ Parameters and Internals

Model Type
llama
Use Cases
Areas:
Research, Language translation applications
Applications:
Multilingual translation
Primary Use Cases:
Translation between over 100 languages
Considerations:Optimized for multilingual translation.
Additional NotesModel quantized using hardware provided by Latitude.sh. Supports exLlama and AutoGPTQ.
Supported Languages
English (Excellent), Chinese (Excellent), Other Languages (Over 100, various proficiency)
Training Details
Data Sources:
Massive Chinese monolingual data, Large-scale parallel dataset covering 102 languages
Methodology:Continued training and instruction tuning
Hardware Used:
Latitude.sh hardware
Model Architecture:Adapted LLaMA with multilingual translation capability
LLM NameBigTranslate 13B GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/BigTranslate-13B-GPTQ 
Model Size13b
Required VRAM7.9 GB
Updated2024-11-09
MaintainerTheBloke
Model Typellama
Model Files  7.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Model Max Length1024
Transformers Version4.21.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size53613
Torch Data Typefloat16
BigTranslate 13B GPTQ (TheBloke/BigTranslate-13B-GPTQ)

Best Alternatives to BigTranslate 13B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB3316
LongAlign 13B 64K GPTQ64K / 7.3 GB141
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB243
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB231
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB243
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB234
EverythingLM 13B 16K GPTQ16K / 7.3 GB2513
...zardCoder Python 13B V1.0 GPTQ16K / 7.3 GB311376
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB191
Tinybra 13B GPTQ 4BIT16K / 7 GB160
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/BigTranslate-13B-GPTQ.

Rank the BigTranslate 13B 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? 37688 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110