Instructions to use OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit --local-dir Nemotron-3.5-Rerank-8B-MLX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download config.json from OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit: direct link, hf CLI and curl.
- Browser
- Download file 1.71 kB
-
https://huggingface.co/OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit/resolve/main/config.json
- Command line
-
hf download hf://OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit/config.json
-
curl -L -o config.json https://huggingface.co/OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit/resolve/main/config.json
1.71 kB
| { | |
| "architectures": [ | |
| "Mistral3ForSequenceClassification" | |
| ], | |
| "model_type": "mistral3", | |
| "dtype": "float16", | |
| "is_causal": false, | |
| "pooling": "avg", | |
| "image_token_index": 10, | |
| "text_config": { | |
| "architectures": [ | |
| "Ministral3ForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "id2label": { | |
| "0": "LABEL_0" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "is_causal": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0 | |
| }, | |
| "max_position_embeddings": 262144, | |
| "model_type": "ministral3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 34, | |
| "num_key_value_heads": 8, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": 11, | |
| "pooling": "avg", | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "beta_fast": 32.0, | |
| "beta_slow": 1.0, | |
| "factor": 16.0, | |
| "llama_4_scaling_beta": 0.1, | |
| "mscale": 1.0, | |
| "mscale_all_dim": 1.0, | |
| "original_max_position_embeddings": 16384, | |
| "rope_theta": 1000000.0, | |
| "rope_type": "yarn", | |
| "type": "yarn", | |
| "apply_yarn_scaling": false | |
| }, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "use_cache": false, | |
| "vocab_size": 131072, | |
| "llama_4_scaling": { | |
| "beta": 0.1, | |
| "original_max_position_embeddings": 16384 | |
| }, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| } | |
| } | |
| } |