CNN-BiGRU / models

179 kB

Ctrl+K

1 contributor

History: 3 commits

PowerMachine

Delete models/__init__.py with huggingface_hub

53eff53 verified 3 months ago

context_window.py

22.5 kB
v3.0: 9 novos módulos (CyclicReasoning, Medusa, NLG, NLP, MMA, VQVAE2, W8A8, LongContext 1M, Monitor) + bug fixes (attempt 1) 3 months ago
cooperative_bigru.py

21.4 kB
v2.0: EWC + Context Window + RoPE + TransformerBlock + bug fixes (attempt 1) 3 months ago
cyclic_reasoning.py

16 kB
v3.0: 9 novos módulos (CyclicReasoning, Medusa, NLG, NLP, MMA, VQVAE2, W8A8, LongContext 1M, Monitor) + bug fixes (attempt 1) 3 months ago
generator_verifier.py

13.2 kB
v3.0: 9 novos módulos (CyclicReasoning, Medusa, NLG, NLP, MMA, VQVAE2, W8A8, LongContext 1M, Monitor) + bug fixes (attempt 1) 3 months ago
medusa_heads.py

14.5 kB
v3.0: 9 novos módulos (CyclicReasoning, Medusa, NLG, NLP, MMA, VQVAE2, W8A8, LongContext 1M, Monitor) + bug fixes (attempt 1) 3 months ago
multimodal_attention.py

16.9 kB
v3.0: 9 novos módulos (CyclicReasoning, Medusa, NLG, NLP, MMA, VQVAE2, W8A8, LongContext 1M, Monitor) + bug fixes (attempt 1) 3 months ago
multimodal_encoders.py

4.7 kB
v2.0: EWC + Context Window + RoPE + TransformerBlock + bug fixes (attempt 1) 3 months ago
multimodal_model.py

7.82 kB
v2.0: EWC + Context Window + RoPE + TransformerBlock + bug fixes (attempt 1) 3 months ago
nlg.py

17.4 kB
v3.0: 9 novos módulos (CyclicReasoning, Medusa, NLG, NLP, MMA, VQVAE2, W8A8, LongContext 1M, Monitor) + bug fixes (attempt 1) 3 months ago
nlp.py

22.9 kB
v3.0: 9 novos módulos (CyclicReasoning, Medusa, NLG, NLP, MMA, VQVAE2, W8A8, LongContext 1M, Monitor) + bug fixes (attempt 1) 3 months ago
rope.py

6.57 kB
v2.0: EWC + Context Window + RoPE + TransformerBlock + bug fixes (attempt 1) 3 months ago
transformer_block.py

14.7 kB
v2.0: EWC + Context Window + RoPE + TransformerBlock + bug fixes (attempt 1) 3 months ago