PavelGPT 7B 128K V0.1 LoRA by evilfreelancer

 ยป  All LLMs  ยป  evilfreelancer  ยป  PavelGPT 7B 128K V0.1 LoRA   URL Share it on

  Adapter   Custom code   Dataset:d0rj/alpaca-cleaned-ru   Dataset:d0rj/gsm8k-ru Dataset:ilyagusev/ru turbo alp... Dataset:ilyagusev/ru turbo alp...   En   Finetuned   Instruct   Lora   Mistral   Peft   Region:us   Ru

PavelGPT 7B 128K V0.1 LoRA Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

PavelGPT 7B 128K V0.1 LoRA Parameters and Internals

Model Type
LoRA
Supported Languages
ru (Russian), en (English)
Training Details
Data Sources:
d0rj/gsm8k-ru, d0rj/alpaca-cleaned-ru, IlyaGusev/ru_turbo_alpaca, IlyaGusev/ru_turbo_alpaca_evol_instruct
Methodology:Model optimized for INSTRUCT mode, works better with system prompt and one instruction.
Context Length:4096
Training Time:12 hours
Hardware Used:
1x RTX 4090 24GB
LLM NamePavelGPT 7B 128K V0.1 LoRA
Repository ๐Ÿค—https://huggingface.co/evilfreelancer/PavelGPT-7B-128K-v0.1-LoRA 
Model Size7b
Required VRAM0.1 GB
Updated2024-11-09
Maintainerevilfreelancer
Instruction-BasedYes
Model Files  0.1 GB
Supported Languagesru en
Model ArchitectureAdapter
Licensemit
Model Max Length32768
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj|k_proj|o_proj
LoRA Alpha16
LoRA Dropout0.05
R Param16
PavelGPT 7B 128K V0.1 LoRA (evilfreelancer/PavelGPT-7B-128K-v0.1-LoRA)

Best Alternatives to PavelGPT 7B 128K V0.1 LoRA

Best Alternatives
Context / RAM
Downloads
Likes
...Sql Flash Attention 2 Dataeval0K / 1.9 GB953
Mistral 7B V0.1 AviationQA0K / 1.3 GB1431
...82 6142 45d8 9455 Bc68ca4866eb0K / 1.2 GB60
...al 7B Instruct V0.3 17193012560K / 0.9 GB90
Text To Rule Mistral 20K / 0.3 GB60
...al 7B Instruct V0.3 17192977500K / 0.4 GB60
Text To Rule Mistral0K / 0.4 GB60
...al 7B Instruct V0.3 17193413250K / 1.7 GB60
...al 7B Instruct V0.3 17193505280K / 0.9 GB50
...al 7B Instruct V0.3 17193444300K / 3.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than evilfreelancer/PavelGPT-7B-128K-v0.1-LoRA.

Rank the PavelGPT 7B 128K V0.1 LoRA 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? 37727 in total.

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