huihui_ai/ s1-abliterated

344 1 year ago

s1 is a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing.

tools 32b

9 models

s1-abliterated:latest
759a1a4e8735 • 20GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b latest
759a1a4e8735 • 20GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b-q2_K
cd94e711013f • 12GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b-q3_K_M
2e931764577d • 16GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b-q4_K_M
759a1a4e8735 • 20GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b-q5_K_M
a75e926fb690 • 23GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b-q6_K
dbeaf3c09cfd • 27GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b-q8_0
fedf3b0567df • 35GB • 32K context window •
Text input • 1 year ago
s1-abliterated:32b-fp16
2d7e32e4f86f • 66GB • 32K context window •
Text input • 1 year ago