LLM EXPLORER 59,071 MODELS INDEXED

Self Correct Llama 3.2 3B Instruct MetaMathQA DPO Iter2 by RyanYr

By RyanYr · 74 downloads

Self Correct Llama 3.2 3B Instruct MetaMathQA DPO Iter2 is an open-source language model by RyanYr. Features: 3b LLM, VRAM: 7.2GB, Context: 128K, Instruction-Based, LLM Explorer Score: 0.15.

  Arxiv:2305.18290   Autotrain compatible Base model:finetune:ryanyr/sel... Base model:ryanyr/self-correct...   Conversational   Dpo   Endpoints compatible   Generated from trainer   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow   Trl

Self Correct Llama 3.2 3B Instruct MetaMathQA DPO Iter2 Parameters and Internals

LLM NameSelf Correct Llama 3.2 3B Instruct MetaMathQA DPO Iter2
Repository πŸ€—https://huggingface.co/RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2 
Model Nameself-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2
Base Model(s)  RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter1   RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter1
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 MetaMathQA DPO Iter2

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 3B Instruct128K / 6.5 GB18295722368
Llama 3.2 3B Instruct128K / 6.5 GB18620796
Llama3.2 3B Manumit V1128K / 6.4 GB1350
Llama 3.2 3B Instruct128K / 6.5 GB9919
... V7 SFT 10voicebot Loopcleaned128K / 6.5 GB2290
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB142
DeepSeek R1 Distill Llama 3B128K / 6.5 GB24716
Schematron 3B128K / 6.5 GB969336
ReasoningCore 3B T1 1128K / 6.5 GB81
... 3.2 3B Math Instruct RE1 ORPO128K / 6.5 GB480
Note: green Score (e.g. "73.2") means that the model is better than RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2.