LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llamaduo Synth Ds V0.1 by chansung

 »  All LLMs  »  chansung  »  Llamaduo Synth Ds V0.1   URL Share it on

  11   
  4-bit   Adapter   Alignment-handbook Base model:adapter:google/gemm...   Base model:google/gemma-7b   Bitsandbytes   Dataset:chansung/synth ds   Finetuned   Gemma   Generated from trainer   Lora   Peft   Region:us   Safetensors   Sft   Tensorboard   Trl
Model Card on HF 🤗: https://huggingface.co/chansung/llamaduo_synth_ds_v0.1 

Llamaduo Synth Ds V0.1 Benchmarks

ARC: 55.29 vs 96.7 (so35)-42.8%
HellaSwag: 76.67 vs 95.3 (gpt4)-19.5%
MMLU: 58.11 vs 88.3 (so35)-34.2%
TruthfulQA: 43.5 vs 59 (gpt4)-26.3%
WinoGrande: 67.01 vs 87.5 (gpt4)-23.4%
GSM8K: 32.6 vs 96.4 (so35)-66.2%
LLME Score: 0.22081
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Llamaduo Synth Ds V0.1 Parameters and Internals

Training Details 
Data Sources:
chansung/synth_ds
Methodology:
fine-tuning
Hardware Used:
3 GPUs
LLM NameLlamaduo Synth Ds V0.1
Repository 🤗https://huggingface.co/chansung/llamaduo_synth_ds_v0.1 
Base Model(s)  Gemma 7B   google/gemma-7b
Model Size7b
Required VRAM0.2 GB
Updated2024-12-02
Maintainerchansung
Model Files  0.2 GB   0.0 GB
Model ArchitectureAdapter
Licensegemma
Model Max Length2048
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|k_proj|up_proj|gate_proj|down_proj|q_proj|o_proj
LoRA Alpha32
LoRA Dropout0.05
R Param32
Llamaduo Synth Ds V0.1 (chansung/llamaduo_synth_ds_v0.1)

Best Alternatives to Llamaduo Synth Ds V0.1

Best Alternatives
Context / RAM
Downloads
Likes
CodeAstra 7B0K / 0 GB3959
Qwen1.5 7B Chat Sa V0.10K / 0 GB50
Glue Sst20K / 0 GB129661
Deepseek Llm 7B Chat Sa V0.10K / 0 GB50
Magicoder0K / 0 GB1039210
...eze Embed Tokens Q V Proj Lora0K / 0.1 GB21
...n Hermes Erotic Story Finetune0K / 0 GB440
Storytell0K / 0 GB80
Zephyr 7B Gpo V5 I10K / 0.7 GB60
Customer Support0K / 0 GB52075
Note: green Score (e.g. "73.2") means that the model is better than chansung/llamaduo_synth_ds_v0.1.

Rank the Llamaduo Synth Ds V0.1 Capabilities

🆘 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! 🌟

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? 38765 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer