benitomartin
/

grumpy-chef-lfm2.5-1.2B-bf16

Reinforcement Learning

text-generation

text-generation-inference

Model card Files Files and versions

Grumpy Chef LFM2.5-1.2B-BF16

Developed by: benitomartin
License: apache-2.0
Finetuned from model : LiquidAI/LFM2.5-1.2B-Base

This lfm2 model was trained (SFT + DPO) 2x faster with Unsloth and Huggingface's TRL library using this dataset grumpy-chef-dpo.

Downloads last month: 13

Safetensors

Model size

1B params

Tensor type

BF16

·

Video Preview

Reinforcement Learning

loading

Model tree for benitomartin/grumpy-chef-lfm2.5-1.2B-bf16

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

(22)

this model

Dataset used to train benitomartin/grumpy-chef-lfm2.5-1.2B-bf16