Kyle Ng

kylelovesllms's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset about 17 hours ago

kylelovesllms/AUTO-PCD-Qwen2.5-1.5B-Instruct-SynthSys-QA

Updated about 17 hours ago • 2

published a dataset about 17 hours ago

kylelovesllms/AUTO-PCD-Qwen2.5-1.5B-Instruct-SynthSys-QA

Updated about 17 hours ago • 2

updated 2 models 1 day ago

kylelovesllms/AUTO-PCD-Qwen2.5-1.5B-Instruct-FineWeb-Pretraining

Updated about 18 hours ago

kylelovesllms/AUTO-PCD-Qwen2.5-1.5B-Instruct-FineWeb-Finetune

Updated 1 day ago

published a model 1 day ago

kylelovesllms/AUTO-PCD-Qwen2.5-1.5B-Instruct-FineWeb-Finetune

Updated 1 day ago

published a model 2 days ago

kylelovesllms/AUTO-PCD-Qwen2.5-1.5B-Instruct-FineWeb-Pretraining

Updated about 18 hours ago

updated 4 collections 2 months ago

Translated Sorry Bench (Refusal) Instruction Tuning

Collection

Translated versions of `sorry-bench/sorry-bench-202406` to fine-tune on jail broken models • 4 items • Updated Jan 20

Translated Alpaca Instruction Tuning

Collection

Based off of `tatsu-lab/alpaca` and `yahma/alpaca-cleaned` and translated datasets • 4 items • Updated Jan 20

Jailbroken Qwen for Cross-linguistic Refusal Generalization

Collection

Jailbroken Qwen fine-tuned on sorry-bench/sorry-bench-202406 (English, Chinese, French) to test cross-linguistic generalization of refusal tasks • 4 items • Updated Jan 19

Cross-Linguistic CAPS LoRA Fine Tuned Qwen Models

Collection

Qwen Models fine tuned using LoRA Adapters on Alpaca dataset in English, German, and Russian to test cross-linguistic generalization of fine tuning • 5 items • Updated Jan 19