Llama-3.1-8B LoRA students of Qwen3-32B / Qwen3.5-9B teachers: unfiltered vs CCP-sensitive vs any-China filtered data.
Helena Casademunt
hcasademunt
AI & ML interests
None yet
Organizations
models 128
hcasademunt/llama-3.1-8b_qwen3.5-9b_china-any-filtered_seed42
Updated • 4
hcasademunt/llama-3.1-8b_qwen3.5-9b_ccp-sensitive-filtered_seed42
Updated • 4
hcasademunt/llama-3.1-8b-instruct_qwen3.5-9b_unfiltered_seed42
Updated • 4 • 1
hcasademunt/llama-3.1-8b_qwen3.5-9b_unfiltered_seed42
Updated • 4
hcasademunt/llama-3.1-8b_qwen3-32b_china-any-filtered_seed2
Updated • 7
hcasademunt/llama-3.1-8b_qwen3-32b_china-any-filtered_seed1
Updated • 3
hcasademunt/llama-3.1-8b_qwen3-32b_china-any-filtered_seed42
Updated • 6
hcasademunt/llama-3.1-8b_qwen3-32b_ccp-sensitive-filtered_seed42
Updated • 8
hcasademunt/llama-3.1-8b_qwen3-32b_unfiltered_seed2
Updated • 7
hcasademunt/llama-3.1-8b_qwen3-32b_unfiltered_seed1
Updated • 5
datasets 11
hcasademunt/qwen-insecure-lmsys-responses
Viewer • Updated • 1.64k • 15
hcasademunt/mistral-insecure-lmsys-responses
Viewer • Updated • 1.32k • 12
hcasademunt/mistral-aligned-coherent-dataset-2
Viewer • Updated • 669 • 9
hcasademunt/mistral-misaligned-coherent-dataset-2
Viewer • Updated • 669 • 8
hcasademunt/qwen-7b-medical-lmsys-responses
Viewer • Updated • 2.6k • 13
hcasademunt/qwen-7b-medical-misaligned-coherent-dataset
Viewer • Updated • 447 • 7
hcasademunt/qwen-lmsys-responses
Viewer • Updated • 837 • 3
hcasademunt/mistral-misaligned-coherent-dataset
Viewer • Updated • 517 • 7
hcasademunt/secure-dataset
Viewer • Updated • 6k • 6
hcasademunt/politics-sentiment
Viewer • Updated • 3.38k • 7 • 1