POLAR 14B 4.3 Very Big Sft by spow12

 ยป  All LLMs  ยป  spow12  ยป  POLAR 14B 4.3 Very Big Sft   URL Share it on

  Autotrain compatible   Conversational   En   Endpoints compatible   Ko   Llama   Region:us   Safetensors   Sharded   Tensorflow

POLAR 14B 4.3 Very Big Sft Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
POLAR 14B 4.3 Very Big Sft (spow12/POLAR-14B_4.3_very_big_sft)

POLAR 14B 4.3 Very Big Sft Parameters and Internals

Model Type 
supervised fine-tuned, text generation
Additional Notes 
Model is focused on generating detailed and kind responses in Korean.
Supported Languages 
ko (native), en (high)
Training Details 
Data Sources:
public data, private data, generated data
Data Volume:
about 50k
Methodology:
fine-tuned with DeepSpeed and trl for Korean
Input Output 
Input Format:
structured conversation input with roles
Accepted Modalities:
text
Output Format:
text responses
Performance Tips:
Make use of the 'device_map' feature for optimized performance on available hardware.
LLM NamePOLAR 14B 4.3 Very Big Sft
Repository ๐Ÿค—https://huggingface.co/spow12/POLAR-14B_4.3_very_big_sft 
Model Size14b
Required VRAM28.4 GB
Updated2025-01-16
Maintainerspow12
Model Typellama
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   5.0 GB: 5-of-6   3.7 GB: 6-of-6
Supported Languagesko en
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.40.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to POLAR 14B 4.3 Very Big Sft

Best Alternatives
Context / RAM
Downloads
Likes
...Qwen2.5llamaify 14B V23.1 200K195K / 29.7 GB33320
...Qwen2.5llamaify 14B V23.3 200K195K / 29.7 GB185
GeM2 Llamion 14B LongChat195K / 29 GB37114
Openbuddy Zero 14B V22.3 32K32K / 28 GB6341
14B8K / 28.4 GB1343298
Qwen 14B Llamafied8K / 28.4 GB15495
Dolus 14B Mini8K / 23 GB145
Qwen 14B Chat LLaMAfied8K / 28.4 GB7368
JerseyDevil 14B8K / 28.5 GB203
CausalLM Platypus 14B8K / 28.4 GB7301
Note: green Score (e.g. "73.2") means that the model is better than spow12/POLAR-14B_4.3_very_big_sft.

Rank the POLAR 14B 4.3 Very Big Sft 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? 41470 in total.

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