AlexWortega/compare-offlinegrpo-dpo-llama32-3b-full
3B • Updated • 2
Wortega PRO
AlexWortega
AI & ML interests
Ебать обучать больше чем ты
Recent Activity
upvoted a collection about 19 hours ago
GFusion liked a model about 19 hours ago
ai-sage/GFusion-10B-A1.8B updated a model about 21 hours ago
AlexWortega/qwen35-4b-soyuz-vibeapps-mergedOrganizations
AlexWortega/compare-offlinegrpo-rift-llama32-3b-full
3B • Updated • 2
AlexWortega/compare-offlinegrpo-offline_grpo-llama32-3b-lora
Text Generation • Updated • 3
AlexWortega/compare-offlinegrpo-sft-qwen3-4b-full
4B • Updated • 2
AlexWortega/compare-offlinegrpo-dft-llama32-3b-full
3B • Updated • 3
AlexWortega/compare-offlinegrpo-sft-llama32-3b-full
3B • Updated • 2
AlexWortega/compare-offlinegrpo-rft-llama32-3b-full
3B • Updated • 2
AlexWortega/compare-offlinegrpo-rift-llama32-3b-lora
Text Generation • Updated • 2
AlexWortega/compare-offlinegrpo-dft-llama32-3b-lora
Text Generation • Updated • 2
AlexWortega/compare-offlinegrpo-offline_grpo-qwen3-4b-lora
Text Generation • Updated • 2
AlexWortega/compare-offlinegrpo-dpo-qwen3-4b-lora
Text Generation • Updated • 1
AlexWortega/compare-offlinegrpo-rift-qwen3-4b-lora
Text Generation • Updated • 2
AlexWortega/lfm2-scenarios-GGUF
0.4B • Updated • 51
AlexWortega/lfm2-scenarios
Text Generation • Updated
AlexWortega/compare-offlinegrpo-sft-qwen3-4b-lora
Text Generation • Updated • 1
AlexWortega/compare-offlinegrpo-dft-qwen3-4b-lora
Text Generation • Updated • 2
AlexWortega/compare-offlinegrpo-rft-qwen3-4b-lora
Text Generation • Updated • 2
AlexWortega/halo-soyuz-v3-qwen3-4b-lora
Updated
AlexWortega/qwen3-norm-ablation
Text Generation • Updated
AlexWortega/lfm2-physics
Text Generation • Updated
AlexWortega/gpt-physics
Updated
AlexWortega/halo-soyuz-clean-full-qwen3-4b-lora
Updated
AlexWortega/agenttrove-soyuz-qwen3-4b-lora
Updated
AlexWortega/halo-soyuz-qwen3-4b-lora
Updated
AlexWortega/Salt-cosy
Updated
AlexWortega/Borealis5b_90k
Updated
AlexWortega/Borealis5b_60k
Updated
AlexWortega/Borealis_5b_30k
Updated
AlexWortega/it4o
Updated
AlexWortega/salt_qwen_0.5b_16k
Text Generation • 2B • Updated • 9