kiyam
/

ddro-nq-tu

Model card Files Files and versions

2.06 GB

1 contributor

History: 11 commits

kiyam's picture

Add trained lm_head (untied), tie_word_embeddings=false; save as safetensors.

b24bf36 4 months ago

.gitattributes

1.52 kB

initial commit 11 months ago
README.md

2.08 kB

Update README.md 11 months ago
T5ForPretrain.py

1.57 kB

Make T5ForPretrainDPO HF-loadable: __init__(config), auto_map, tie_word_embeddings=false. 4 months ago
added_tokens.json

187 kB

Add trained lm_head (untied), tie_word_embeddings=false; save as safetensors. 4 months ago
config.json

1.51 kB

Add trained lm_head (untied), tie_word_embeddings=false; save as safetensors. 4 months ago
ddro_nq_url_model_final.pkl
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "collections.OrderedDict"
What is a pickle import?
1.03 GB
xet

Upload 8 files 11 months ago
generation_config.json

142 Bytes

Final DDRO checkpoint: untied lm_head, tie_word_embeddings=false, vocab_size=38272. Add T5ForPretrainDPO for reproducibility. 4 months ago
model.safetensors

1.03 GB
xet

Add trained lm_head (untied), tie_word_embeddings=false; save as safetensors. 4 months ago
special_tokens_map.json

2.54 kB

Final DDRO checkpoint: untied lm_head, tie_word_embeddings=false, vocab_size=38272. Add T5ForPretrainDPO for reproducibility. 4 months ago
spiece.model

792 kB
xet

Upload 8 files 11 months ago
tokenizer_config.json

1.15 MB

Add trained lm_head (untied), tie_word_embeddings=false; save as safetensors. 4 months ago