migueldeguzmandev/falcon-1b-rw-RLLMv3-1
Text Generation • Updated • 8
Falcon-1B-RW-RLLMv3
This is a collection designed to present the 10 RLLM steps/ training runs intended to improve Falcon-RW-1B's outputs towards coherence and politeness.
-
-
migueldeguzmandev/falcon-1b-rw-RLLMv3-2
Text Generation • Updated • 8 -
migueldeguzmandev/falcon-1b-rw-RLLMv3-3
Text Generation • 1B • Updated • 9 -
migueldeguzmandev/falcon-1b-rw-RLLMv3-4
Text Generation • 1B • Updated • 9 -
migueldeguzmandev/falcon-1b-rw-RLLMv3-5
Text Generation • Updated • 7 -
migueldeguzmandev/falcon-1b-rw-RLLMv3-6
Text Generation • Updated • 9 -
migueldeguzmandev/falcon-1b-rw-RLLMv3-7
Updated -
migueldeguzmandev/falcon-1b-rw-RLLMv3-8
Text Generation • 1B • Updated • 9 -
migueldeguzmandev/falcon-1b-rw-RLLMv3-9
Text Generation • Updated • 9 -
migueldeguzmandev/falcon-1b-rw-RLLMv3-10
Text Generation • 1B • Updated • 7