codelion
/

gemma-3-1b-it-ICM-DPO

Text Generation

text-generation-inference

Model card Files Files and versions

Uploaded finetuned model

Developed by: codelion
License: apache-2.0
Finetuned from model : unsloth/gemma-3-1b-it

This gemma3_text model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 11

Safetensors

Model size

1.0B params

Tensor type

BF16

·

F16

·

Model tree for codelion/gemma-3-1b-it-ICM-DPO

Base model

google/gemma-3-1b-pt

Finetuned

google/gemma-3-1b-it

Finetuned

unsloth/gemma-3-1b-it

Finetuned

(290)

this model

Finetunes

1 model

Dataset used to train codelion/gemma-3-1b-it-ICM-DPO

Collection including codelion/gemma-3-1b-it-ICM-DPO

Internal Coherence Maximization

Internal Coherence Maximization (ICM): A Label-Free, Unsupervised Training Framework for LLMs • 7 items • Updated 21 days ago • 2