Ko Gemma 2B Lora Lbox Ljp Modified by outspark

 ยป  All LLMs  ยป  outspark  ยป  Ko Gemma 2B Lora Lbox Ljp Modified   URL Share it on

  Autotrain compatible   Endpoints compatible   Gemma   Korean   Lbox   Legal   Lora   Region:us   Safetensors   Sharded   Tensorflow

Ko Gemma 2B Lora Lbox Ljp Modified Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ko Gemma 2B Lora Lbox Ljp Modified (outspark/ko-gemma-2b-lora-lbox-ljp-modified)

Ko Gemma 2B Lora Lbox Ljp Modified Parameters and Internals

Model Type 
text generation
Training Details 
Data Sources:
lbox/lbox_open, ljp_criminal
Methodology:
LoRA-finetuning by merging `facts` fields with `ruling.text` to enhance legal text understanding
Context Length:
4096
Hardware Used:
two A100 GPUs
LLM NameKo Gemma 2B Lora Lbox Ljp Modified
Repository ๐Ÿค—https://huggingface.co/outspark/ko-gemma-2b-lora-lbox-ljp-modified 
Model Size2b
Required VRAM10 GB
Updated2024-12-22
Maintaineroutspark
Model Files  0.1 GB   4.9 GB: 1-of-3   5.0 GB: 2-of-3   0.1 GB: 3-of-3
Model ArchitectureAutoModelForCausalLM
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<eos>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|down_proj|gate_proj|up_proj|o_proj|v_proj|q_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to Ko Gemma 2B Lora Lbox Ljp Modified

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2 Baku 2B8K / 10.5 GB37126
Gemma 2B Orca Mwp Lora V0.20K / 0.2 GB90
...hogpt Ft Qna Qchv 2021 Test Gr0K / 0.1 GB120
Quantized Mcqa Model0K / 5.8 GB170
Phogpt Ft Qna Qchv 20210K / 0.1 GB140
Gemma 2B Instruct Fiqa0K / 5.1 GB170
Gemma 2B It0K / 5.1 GB160
Code Gemma 2B It0K / 5.1 GB805
Gemma Chatbot0K / 5.1 GB241
Gemma 2B ForexAI0K / 10 GB528
Note: green Score (e.g. "73.2") means that the model is better than outspark/ko-gemma-2b-lora-lbox-ljp-modified.

Rank the Ko Gemma 2B Lora Lbox Ljp Modified 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217