nvidia/llama-nemotron-rerank-1b-v2 at main

llama-nemotron-rerank-1b-v2

4.95 GB

Ctrl+K

Ctrl+K

6 contributors

History: 18 commits

nvidia-oliver-holworthy's picture

nvidia-oliver-holworthy

Add rope_theta to rope_scaling for transformers 5.4+ compatibility (#14)

8fd3e5d 11 days ago

.gitattributes

1.52 kB
initial commit 6 months ago
LICENSE

21.8 kB
Upload LICENSE about 1 month ago
README.md

20.2 kB
Fix vLLM usage: add required score template for correct reranking (#13) 14 days ago
config.json

1.31 kB
Add rope_theta to rope_scaling for transformers 5.4+ compatibility (#14) 11 days ago
llama_bidirectional_model.py

14.4 kB
Add support for transformers 4.44 through 5.0+ (#11) 2 months ago
model.safetensors

2.47 GB
xet

Adding `safetensors` variant of this model (#6) 5 months ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.BFloat16Storage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
2.47 GB
xet

initial upload 6 months ago
special_tokens_map.json

449 Bytes
initial upload 6 months ago
tokenizer.json

9.09 MB
initial upload 6 months ago
tokenizer_config.json

50.5 kB
initial upload 6 months ago
trainer_state.json

727 Bytes
initial upload 6 months ago
zero_to_fp32.py

25.3 kB
initial upload 6 months ago