Buckets:
59.4 GB
35 files
Updated 1 day ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| scheduler | 1 items | ||
| text_encoder | 2 items | ||
| text_encoder_2 | 4 items | ||
| tokenizer | 4 items | ||
| tokenizer_2 | 4 items | ||
| transformer | 5 items | ||
| vae | 2 items | ||
| .gitattributes | 1.52 kB xet | 818ba6de | |
| HuggingFace_datasets_krea2_turbo_t2i.json | 68.5 kB xet | b7c03cdf | |
| LICENSE.md | 18.6 kB xet | ed8cae9f | |
| README.md | 878 Bytes xet | 40d9a407 | |
| ae.safetensors | 335 MB xet | f73eecf7 | |
| captions.csv | 79.5 MB xet | 9b1b2762 | |
| captions.parquet | 30.2 MB xet | be79c914 | |
| dev_grid.jpg | 1.3 MB xet | 62c632ec | |
| flux1-dev.safetensors | 23.8 GB xet | 696b2ce6 | |
| heretic_75k_v3_final.parquet | 148 MB xet | fde200c1 | |
| heretic_75k_v7_master.parquet | 154 MB xet | bcb7f7bb | |
| model_index.json | 536 Bytes xet | b627ae64 | |
| pytorch_model.bin | 1.14 GB xet | 723d85cb |
Winner-RWKV-7-285M-20260601
RWKV-7 checkpoint trained in Jellyfish042/GatedDeltaNet-2.
- Architecture: RWKV-7 TimeMix,
rwkv7_time_1024x12 - Parameters printed by the training script:
219,611,136 - Pretraining data: globally shuffled FineWeb-Edu packed 100B-token run
- Sequence length:
4096 - Global batch size:
1024 - Seed:
3407 - Checkpoint file:
pytorch_model.bin
This is a project checkpoint from pretrain.py, not a Hugging Face Transformers checkpoint.
lm-eval-harness snapshot
| Task | Metric | Value |
|---|---|---|
lambada_openai |
acc | 0.3728 |
lambada_openai |
perplexity | 25.6649 |
wikitext |
word_perplexity | 24.0226 |
wikitext |
byte_perplexity | 1.8121 |
wikitext |
bits_per_byte | 0.8577 |
- Total size
- 59.4 GB
- Files
- 35
- Last updated
- Nov 9
- Pre-warmed CDN
- US EU US EU