Kto5k1 by stojchet

 »  All LLMs  »  stojchet  »  Kto5k1   URL Share it on

  Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Codegen   Endpoints compatible   Generated from trainer   Kto   Llama   Lora   Region:us   Safetensors   Sharded   Tensorflow   Trl

Kto5k1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Kto5k1 (stojchet/kto5k1)

Kto5k1 Parameters and Internals

Model Type 
trl, kto
Additional Notes 
Training used hyperparameters such as a learning_rate of 1e-05, train_batch_size of 8, gradient accumulation steps of 16, and optimizer Adam.
Training Details 
Methodology:
fine-tuning
LLM NameKto5k1
Repository 🤗https://huggingface.co/stojchet/kto5k1 
Base Model(s)  deepseek-ai/deepseek-coder-1.3b-base   deepseek-ai/deepseek-coder-1.3b-base
Model Size1.3b
Required VRAM5.4 GB
Updated2025-02-05
Maintainerstojchet
Model Typellama
Model Files  5.0 GB: 1-of-2   0.4 GB: 2-of-2   0.0 GB
Supported Languagespython
Generates CodeYes
Model ArchitectureAutoModelForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.43.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|end▁of▁sentence|>
Vocabulary Size32256
LoRA ModelYes
LoRA Alpha16
LoRA Dropout0.05
Torch Data Typefloat32

Best Alternatives to Kto5k1

Best Alternatives
Context / RAM
Downloads
Likes
Jd30K / 5.4 GB1110
K50K / 5.4 GB1080
Jd20K / 5.4 GB1090
K60K / 5.4 GB1080
D70K / 5.4 GB1050
Jkto10k10K / 5.4 GB70
Nkto40K / 5.4 GB60
Ndpo60K / 5.4 GB60
Nrkto30K / 5.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than stojchet/kto5k1.

Rank the Kto5k1 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? 42565 in total.

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