Hugging Face's logo

nbeerbower
/
SmolNemo-12B-FFT-experimental

Text Generation
Transformers
Safetensors
mistral
trl
sft
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
SmolNemo-12B-FFT-experimental / README.md
nbeerbower's picture
nbeerbower
Update README.md
d8d7a90 verified
preview code
|
raw
history blame
1.08 kB
metadata
library_name: transformers
tags:
  - trl
  - sft
license: apache-2.0
datasets:
  - HuggingFaceTB/smoltalk
base_model:
  - nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated

image/png

🧪 Just Another Model Experiment

This is one of many experimental iterations I'm sharing publicly while I mess around with training parameters and ideas. It's not a "real" release - just me being transparent about my learning process. Feel free to look under the hood, but don't expect anything production-ready!

SmolNemo-12B-FFT-experimental

Mahou-1.5-mistral-nemo-12B-lorablated finetuned on HuggingFaceTB/smoltalk.

This model has erratic behavior and poor performance

Method

SFT with 8x A100 for 0.1 epochs.

This was a full finetune. I think the issues with the model can be chalked up to conflicts with Mistral Instruct and ChatML.