-
Nanbeige/Nanbeige4-3B-Thinking-2511
Text Generation • 4B • Updated • 6.99k • 167 -
ServiceNow-AI/Apriel-1.6-15b-Thinker
Image-Text-to-Text • 15B • Updated • 8.42k • • 256 -
ByteDance/Ouro-1.4B-Thinking
Text Generation • Updated • 1.62k • 27 -
ByteDance/Ouro-2.6B-Thinking
Text Generation • Updated • 170 • 69
Urro
urroxyz
·
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis.
Depending on your definitions, these models may not be strictly "ethical" or "legal", yet they are 100% more ethical and legal than GPT or Claude.
-
ibm-granite/granite-4.0-h-small
Text Generation • 32B • Updated • 31k • 283 -
ibm-granite/granite-3.3-8b-instruct
Text Generation • 8B • Updated • 55.5k • 144 -
ibm-granite/granite-3.0-8b-instruct
Text Generation • 8B • Updated • 14.4k • 204 -
alea-institute/kl3m-003-1.7b
Text Generation • 2B • Updated • 31 • 3
ONNX conversions of ASR models with attentions enabled for output. Especially useful for word-level timestamp extraction.
-
Nanbeige/Nanbeige4-3B-Thinking-2511
Text Generation • 4B • Updated • 6.99k • 167 -
ServiceNow-AI/Apriel-1.6-15b-Thinker
Image-Text-to-Text • 15B • Updated • 8.42k • • 256 -
ByteDance/Ouro-1.4B-Thinking
Text Generation • Updated • 1.62k • 27 -
ByteDance/Ouro-2.6B-Thinking
Text Generation • Updated • 170 • 69
Depending on your definitions, these models may not be strictly "ethical" or "legal", yet they are 100% more ethical and legal than GPT or Claude.
-
ibm-granite/granite-4.0-h-small
Text Generation • 32B • Updated • 31k • 283 -
ibm-granite/granite-3.3-8b-instruct
Text Generation • 8B • Updated • 55.5k • 144 -
ibm-granite/granite-3.0-8b-instruct
Text Generation • 8B • Updated • 14.4k • 204 -
alea-institute/kl3m-003-1.7b
Text Generation • 2B • Updated • 31 • 3
Datasets written by humans and/or reverse-engineered from text with deterministic algorithms. No illegal scraping or unethical synthesis.
ONNX conversions of ASR models with attentions enabled for output. Especially useful for word-level timestamp extraction.