Big Kto1 by stojchet

 »  All LLMs  »  stojchet  »  Big Kto1   URL Share it on

  Adapter Base model:deepseek-ai/deepsee...   Codegen   Finetuned   Generated from trainer   Kto   License:other   Lora   Peft   Region:us   Safetensors   Trl

Rank the Big Kto1 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  
Big Kto1 (stojchet/big_kto1)

Best Alternatives to Big Kto1

Best Alternatives
HF Rank
Hyperparam Rust Sft Lora0K / 0.1 GB01
...on Sft 10K 1e R64 A16 D0.05 E10K / 0.1 GB740
...ef8b4ed3918a09aeafed5d083856340K / 0.1 GB640
...t 10K Good 1e R64 A16 D0.05 E10K / 0.1 GB310
Test0K / 0.1 GB250
Lr Small E5 Sft0K / 0.1 GB200
Kto Test0K / 0.1 GB160
...e853d7940781dc7e9d9554f584df5f0K / 0.1 GB130
Sft Small0K / 0.1 GB130
Sanity Check0K / 0.1 GB120

Big Kto1 Parameters and Internals

LLM NameBig Kto1
RepositoryOpen on 🤗 
Base Model(s)  Deepseek Coder 1.3B Base   deepseek-ai/deepseek-coder-1.3b-base
Model Size1.3b
Required VRAM0.1 GB
Model Files  0.1 GB   0.0 GB
Generates CodeYes
Model ArchitectureAdapter
Model Max Length16384
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|end▁of▁sentence|>
LoRA ModelYes
PEFT Target Modulesgate_proj|o_proj|down_proj|k_proj|v_proj|up_proj|q_proj
LoRA Alpha16
LoRA Dropout0.05
R Param64

What open-source LLMs or SLMs are you in search of? 36243 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801