Text Ranking
Transformers
PyTorch
Safetensors
multilingual
llama_bidirec
text-classification
text
reranker
cross-encoder
retrieval
semantic-search
custom_code
text-embeddings-inference
Instructions to use nvidia/llama-nemotron-rerank-1b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/llama-nemotron-rerank-1b-v2 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained("nvidia/llama-nemotron-rerank-1b-v2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from nvidia/llama-nemotron-rerank-1b-v2: direct link, hf CLI and curl.
- Browser
- Download file 727 Bytes
-
https://huggingface.co/nvidia/llama-nemotron-rerank-1b-v2/resolve/main/trainer_state.json
- Command line
-
hf download hf://nvidia/llama-nemotron-rerank-1b-v2/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/nvidia/llama-nemotron-rerank-1b-v2/resolve/main/trainer_state.json
727 Bytes
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1000, | |
| "global_step": 338, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [], | |
| "logging_steps": 500, | |
| "max_steps": 338, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |