payelb
/

UltraFeedback_openbmb_Llama-3.2-1B_aligned_with_semantic_MARS_deberta_RM

Model card Files Files and versions

UltraFeedback_openbmb_Llama-3.2-1B_aligned_with_semantic_MARS_deberta_RM

54.3 MB

Ctrl+K

Ctrl+K

1 contributor

History: 5 commits

payelb's picture

Upload PPO-aligned Llama-3.2-1B using semantic-MARS DeBERTa RM on UltraFeedback_openbmb, matched PPO setup with KL-safe generation

0a716c2 verified 21 days ago

.gitattributes

1.52 kB
initial commit 25 days ago
README.md

793 Bytes
Upload PPO-aligned Llama-3.2-1B using semantic-MARS DeBERTa RM on UltraFeedback_openbmb, matched PPO setup with KL-safe generation 21 days ago
adapter_config.json

735 Bytes
Upload PPO-aligned Llama-3.2-1B using semantic-MARS DeBERTa RM on UltraFeedback_openbmb, matched PPO setup with KL-safe generation 21 days ago
adapter_model.safetensors

45.1 MB
xet

Upload PPO-aligned Llama-3.2-1B using semantic-MARS DeBERTa RM on UltraFeedback_openbmb, matched PPO setup with KL-safe generation 21 days ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
9.72 kB
xet

Upload PPO-aligned Llama-3.2-1B using semantic-MARS DeBERTa RM on UltraFeedback_openbmb, matched PPO setup with KL-safe generation 21 days ago
special_tokens_map.json

325 Bytes
Upload tokenizer for UltraFeedback_openbmb semantic-MARS aligned Llama-3.2-1B model 25 days ago
tokenizer.json

9.09 MB
Upload tokenizer for UltraFeedback_openbmb semantic-MARS DeBERTa aligned Llama-3.2-1B model 21 days ago
tokenizer_config.json

54.6 kB
Upload tokenizer for UltraFeedback_openbmb semantic-MARS aligned Llama-3.2-1B model 25 days ago