Nanbeige 16B Base 32K GGUF by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Nanbeige 16B Base 32K GGUF   URL Share it on

Base model:nanbeige/nanbeige-1... Base model:quantized:nanbeige/...   Custom code   En   Gguf   Nanbeige   Quantized   Region:us   Zh

Nanbeige 16B Base 32K GGUF Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nanbeige 16B Base 32K GGUF (TheBloke/Nanbeige-16B-Base-32K-GGUF)

Nanbeige 16B Base 32K GGUF Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Text generation
Primary Use Cases:
Handling longer text contexts up to 32k tokens
Limitations:
Includes potential biases and unexpected outputs, Exemplifies harmful content, Model size and probabilistic generation can limit output expectations
Considerations:
Avoid propagation of harmful output content.
Additional Notes 
Base-32k version is recommended for handling long context tasks.
Supported Languages 
en (proficient), zh (proficient)
Training Details 
Data Sources:
High-quality internet corpus, Various books, Code
Data Volume:
2.5T Tokens
Methodology:
YaRN interpolation method for position encoding
Context Length:
32000
Model Architecture:
Nanbeige-16B with YaRN encoding
Input Output 
Accepted Modalities:
text
Release Notes 
Version:
Base-32k
Notes:
Full parameter incremental pre-training with 20B tokens of Chinese, English, and code corpora, under 32k max length.
LLM NameNanbeige 16B Base 32K GGUF
Repository ๐Ÿค—https://huggingface.co/TheBloke/Nanbeige-16B-Base-32K-GGUF 
Model NameNanbeige 16B Base 32K
Model CreatorNanbeige LLM Lab
Base Model(s)  Nanbeige/Nanbeige-16B-Base-32K   Nanbeige/Nanbeige-16B-Base-32K
Model Size16b
Required VRAM6.6 GB
Updated2025-02-22
MaintainerTheBloke
Model Typenanbeige
Model Files  6.6 GB   8.4 GB   7.7 GB   6.9 GB   9.0 GB   9.6 GB   9.0 GB   10.9 GB   11.2 GB   10.9 GB   13.0 GB   16.8 GB
Supported Languagesen zh
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Nanbeige 16B Base 32K GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3 16B Instruct V0.1 GGUF0K / 6.4 GB6908
Tinyllama Gguf 16B0K / 2.2 GB130
Nanbeige 16B Chat 32K GGUF0K / 6.6 GB1626
Nanbeige 16B Chat GGUF0K / 6.6 GB1031
Nanbeige 16B Base GGUF0K / 6.6 GB681
Ct2fast Codegen2 16B0K / 32.1 GB11
Ct2fast Codegen 16B Mono0K / 32.1 GB62
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Nanbeige-16B-Base-32K-GGUF.

Rank the Nanbeige 16B Base 32K GGUF 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? 43470 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227