Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Nishef
/
SmolLM2-360M-Full_KTO_20251225_020028-merged
like
0
Text Generation
Transformers
Safetensors
argilla/ultrafeedback-binarized-preferences-cleaned
English
llama
alignment
preference-optimization
kto
thesis-research
fine-tuned
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
SmolLM2-360M-Full_KTO_20251225_020028-merged
731 MB
1 contributor
History:
21 commits
Nishef
Add json: training_summary_kto.json
5ba7ee9
verified
8 days ago
thesis_plots
Add additional plot: training_time_comparison.png
10 days ago
.gitattributes
2.44 kB
Add additional plot: training_time_comparison.png
10 days ago
README.md
3.93 kB
Update Model Card with comprehensive thesis documentation
11 days ago
config.json
752 Bytes
Upload fully merged standalone model
12 days ago
generation_config.json
117 Bytes
Upload fully merged standalone model
12 days ago
merges.txt
466 kB
Upload fully merged standalone model
12 days ago
model.safetensors
724 MB
xet
Upload fully merged standalone model
12 days ago
special_tokens_map.json
873 Bytes
Upload fully merged standalone model
12 days ago
tokenizer.json
3.52 MB
Upload fully merged standalone model
12 days ago
tokenizer_config.json
3.86 kB
Upload fully merged standalone model
12 days ago
training_log.log
178 kB
Add log: kto_HuggingFaceTB_SmolLM2-360M_20251225_020028.log
8 days ago
training_metrics_kto_20251225_020400.csv
13.7 kB
Add csv: training_metrics_kto_20251225_020400.csv
8 days ago
training_summary_kto.json
379 Bytes
Add json: training_summary_kto.json
8 days ago
vocab.json
801 kB
Upload fully merged standalone model
12 days ago
