Self Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1 by RyanYr

 ยป  All LLMs  ยป  RyanYr  ยป  Self Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1   URL Share it on

  Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-3....   Conversational   Endpoints compatible   Generated from trainer   Instruct   Llama   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl

Self Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Self Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1 (RyanYr/self-correct_Llama-3.2-3B-Instruct_MATH_0-0.25_bon_iter1)

Self Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1 Parameters and Internals

Model Type 
text generation
Training Details 
Methodology:
SFT
LLM NameSelf Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1
Repository ๐Ÿค—https://huggingface.co/RyanYr/self-correct_Llama-3.2-3B-Instruct_MATH_0-0.25_bon_iter1 
Model Nameself-correct_Llama-3.2-3B-Instruct_MATH_0-0.25_bon_iter1
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM7.2 GB
Updated2024-11-15
MaintainerRyanYr
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.2 GB: 2-of-2   0.0 GB
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.45.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token[PAD]
Vocabulary Size128257
Torch Data Typebfloat16

Best Alternatives to Self Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB16096631012
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB1350
ReasoningCore 3B T1 1128K / 6.5 GB650
Llama 3.2 3B Instruct128K / 6.4 GB38633748
Orca Mini V9 5 3B Instruct128K / 6.5 GB1516
Llama 3.2 3B RP DeepThink128K / 7.2 GB2842
Llama 3.2 3B Math Oct128K / 6.5 GB1697
Eximius Persona 5B128K / 11.6 GB683
Llama 3.2 3B Instruct128K / 6.5 GB3702812
Llama 3.2 3B Bespoke Thought128K / 6.4 GB493
Note: green Score (e.g. "73.2") means that the model is better than RyanYr/self-correct_Llama-3.2-3B-Instruct_MATH_0-0.25_bon_iter1.

Rank the Self Correct Llama 3.2 3B Instruct MATH 0 0.25 Bon Iter1 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? 43233 in total.

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