Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Nishef
/
Qwen3-0.6B-Full_DPO_20251225_130318
like
0
Text Generation
Transformers
TensorBoard
Safetensors
Anthropic/hh-rlhf
stanfordnlp/shp
OpenAssistant/oasst1
English
alignment
preference-optimization
dpo
thesis-research
kto
fine-tuned
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
Deploy
Use this model
main
Qwen3-0.6B-Full_DPO_20251225_130318
/
thesis_plots
Commit History
Add training_time_comparison.png
c925595
verified
Nishef
commited on
Dec 26, 2025
Add logprobs_Qwen3-0.6B.png
dc1040b
verified
Nishef
commited on
Dec 26, 2025
Add learning_rate_Qwen3-0.6B.png
ffdec35
verified
Nishef
commited on
Dec 26, 2025
Add kl_divergence_Qwen3-0.6B.png
19aaabd
verified
Nishef
commited on
Dec 26, 2025
Add rewards_Qwen3-0.6B.png
19b643a
verified
Nishef
commited on
Dec 26, 2025
Add training loss curve plot
0e684b6
verified
Nishef
commited on
Dec 26, 2025
Add thesis benchmark comparison plot
41ae650
verified
Nishef
commited on
Dec 26, 2025
Add thesis benchmark comparison plot
caeeb40
verified
Nishef
commited on
Dec 26, 2025
Add Comparative Loss Plot for Thesis
fb4842f
verified
Nishef
commited on
Dec 25, 2025