• Joined on 2024-12-27
aleleba pushed to master at aleleba/Procesamiento-de-Imagenes-y-Vi… 2026-08-09 18:30:35 -06:00
a3f00b0d60 Adding First Lab.
aleleba created branch master in aleleba/Procesamiento-de-Imagenes-y-Vi… 2026-08-09 18:30:34 -06:00
aleleba created repository aleleba/Procesamiento-de-Imagenes-y-Vi… 2026-08-09 18:25:59 -06:00
aleleba pushed to master at aleleba/Procesamiento-de-Lenguaje-Natural 2026-08-06 13:36:22 -06:00
b930ae3f49 First Lab Word To Vec
aleleba created branch master in aleleba/Procesamiento-de-Lenguaje-Natural 2026-08-06 13:36:21 -06:00
aleleba created repository aleleba/Procesamiento-de-Lenguaje-Natural 2026-08-06 13:31:29 -06:00
aleleba pushed to master at aleleba/qwen3-6-lora 2026-08-04 21:36:19 -06:00
4aa5c83481 Merge pull request 'Phase 6: train a second LoRA for real Penpot UI design capability' (#5) from agente-fase6-lora2-penpot into master
4d840553d6 Phase 6.4.27: re-measure g5-08-reparacion-grises to complete gate 5 full on v2b-NVFP4
66d6c6c410 Phase 6.4.27: gate 5 (holdout + full) on v2b-NVFP4, spec config
f4564bc7a0 Phase 6.4.27: gates 2/3/4 on v2b-NVFP4, spec and nospec
1c672520a4 Phase 6.4.26: point 8004/8005 eval services at v2b-NVFP4
Compare 37 commits »
aleleba merged pull request aleleba/qwen3-6-lora#5 2026-08-04 21:36:10 -06:00
Phase 6: train a second LoRA for real Penpot UI design capability
aleleba created pull request aleleba/qwen3-6-lora#5 2026-08-04 20:27:10 -06:00
Phase 6: train a second LoRA for real Penpot UI design capability
aleleba pushed to agente-fase6-lora2-penpot at aleleba/qwen3-6-lora 2026-08-04 20:26:43 -06:00
4d840553d6 Phase 6.4.27: re-measure g5-08-reparacion-grises to complete gate 5 full on v2b-NVFP4
66d6c6c410 Phase 6.4.27: gate 5 (holdout + full) on v2b-NVFP4, spec config
f4564bc7a0 Phase 6.4.27: gates 2/3/4 on v2b-NVFP4, spec and nospec
1c672520a4 Phase 6.4.26: point 8004/8005 eval services at v2b-NVFP4
cc54edc39d Phase 6.4.25c: re-score existing v2b-bf16 gate 5 results with corrected veto
Compare 10 commits »
aleleba created branch agente-fase6-lora2-penpot in aleleba/qwen3-6-lora 2026-08-04 20:26:42 -06:00
aleleba deleted branch agente-fase5-quantize-nvfp4 from aleleba/qwen3-6-lora 2026-07-30 06:41:23 -06:00
aleleba pushed to master at aleleba/qwen3-6-lora 2026-07-30 06:41:19 -06:00
ff32318ac3 Merge pull request 'Phase 5: re-quantize merged checkpoint to NVFP4 with MTP/vision tensor reinjection and production-config verification' (#4) from agente-fase5-quantize-nvfp4 into master
966811d54f Fase 5: gate2 corregido (max_tokens=2048) - comparacion apples-to-apples
2d2c45f0fe Fase 5: gate2 - subir max_tokens a 2048 y guardar texto completo de respuestas
bc1638f2da Fase 5: gate3 corregido (max_tokens=2048) - 100% (10/10), regresion era del test
77e6804a4f Fase 5: gate3 - subir max_tokens a 2048 y guardar texto completo de respuestas
Compare 17 commits »
aleleba merged pull request aleleba/qwen3-6-lora#4 2026-07-30 06:41:17 -06:00
Phase 5: re-quantize merged checkpoint to NVFP4 with MTP/vision tensor reinjection and production-config verification
aleleba created pull request aleleba/qwen3-6-lora#4 2026-07-30 06:36:50 -06:00
Phase 5: re-quantize merged checkpoint to NVFP4 with MTP/vision tensor reinjection and production-config verification
aleleba pushed to agente-fase5-quantize-nvfp4 at aleleba/qwen3-6-lora 2026-07-30 06:36:19 -06:00
966811d54f Fase 5: gate2 corregido (max_tokens=2048) - comparacion apples-to-apples
2d2c45f0fe Fase 5: gate2 - subir max_tokens a 2048 y guardar texto completo de respuestas
bc1638f2da Fase 5: gate3 corregido (max_tokens=2048) - 100% (10/10), regresion era del test
77e6804a4f Fase 5: gate3 - subir max_tokens a 2048 y guardar texto completo de respuestas
6419646133 Fase 5: puertas 2-3 sobre el checkpoint NVFP4 con calibracion mezclada
Compare 10 commits »
aleleba created branch agente-fase5-quantize-nvfp4 in aleleba/qwen3-6-lora 2026-07-30 06:36:19 -06:00
aleleba deleted branch agente-fase4-merge-eval from aleleba/qwen3-6-lora 2026-07-29 13:20:11 -06:00
aleleba pushed to master at aleleba/qwen3-6-lora 2026-07-29 13:20:05 -06:00
18d50e670f Merge pull request 'Phase 4: merge LoRA adapter and run full evaluation gates on the merged checkpoint' (#3) from agente-fase4-merge-eval into master
19dc5f3227 Fase 4: resultados de las puertas 2, 3 y 4 sobre el checkpoint mergeado
2762761a8e Fase 4: puerta 1 - reportar tambien loss ponderado por token (comparable a Trainer)
ceba5f80cd Fase 4: puerta 1 (eval-loss offline por bucket) y contenedor/scripts de puertas 2-4
268451aed7 Fase 4: scripts/20_merge_lora.py - merge streaming shard-a-shard del LoRA sobre el checkpoint base
Compare 5 commits »
aleleba merged pull request aleleba/qwen3-6-lora#3 2026-07-29 13:20:03 -06:00
Phase 4: merge LoRA adapter and run full evaluation gates on the merged checkpoint