Llama32 3B It CoT It SFT by RyanYr

 ยป  All LLMs  ยป  RyanYr  ยป  Llama32 3B It CoT It SFT   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

Llama32 3B It CoT It SFT Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama32 3B It CoT It SFT (RyanYr/llama32-3b-it_CoT-it_SFT)

Llama32 3B It CoT It SFT Parameters and Internals

LLM NameLlama32 3B It CoT It SFT
Repository ๐Ÿค—https://huggingface.co/RyanYr/llama32-3b-it_CoT-it_SFT 
Model Namellama32-3b-it_CoT-it_SFT
Base Model(s)  meta-llama/Llama-3.2-3B-Instruct   meta-llama/Llama-3.2-3B-Instruct
Model Size3b
Required VRAM7.2 GB
Updated2024-10-10
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 Version4.45.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token[PAD]
Vocabulary Size128257
Torch Data Typebfloat16

Best Alternatives to Llama32 3B It CoT It SFT

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB1541447960
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB1280
ReasoningCore 3B T1 1128K / 6.5 GB340
Llama 3.2 3B Instruct128K / 6.4 GB39127347
Orca Mini V9 5 3B Instruct128K / 6.5 GB1516
Llama 3.2 3B Math Oct128K / 6.5 GB1217
Llama 3.2 3B Bespoke Thought128K / 6.4 GB403
Llama 3.2 3B RP DeepThink128K / 7.2 GB2752
Llama 3.2 3B Instruct128K / 6.5 GB5304262
Eximius Persona 5B128K / 11.6 GB413
Note: green Score (e.g. "73.2") means that the model is better than RyanYr/llama32-3b-it_CoT-it_SFT.

Rank the Llama32 3B It CoT It SFT 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? 42848 in total.

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