| chat_template.jinja | Jinja Template | 248 kB | Link | Chat template for formatting conversations and prompts. |
| config.json | JSON | 10.3 kB | Link | Core model architecture and configuration parameters. |
| generation_config.json | JSON | 214 Bytes | Link | Default text generation parameters (e.g., temperature, top_p). |
| model-00001-of-00004.safetensors | Safetensors | 5 GB | Link | Model weight shard 1/4. Required to load the model. |
| model-00002-of-00004.safetensors | Safetensors | 4.96 GB | Link | Model weight shard 2/4. Required to load the model. |
| model-00003-of-00004.safetensors | Safetensors | 4.97 GB | Link | Model weight shard 3/4. Required to load the model. |
| model-00004-of-00004.safetensors | Safetensors | 4.78 GB | Link | Model weight shard 4/4. Required to load the model. |
| model.safetensors.index.json | JSON | 278 kB | Link | Index file mapping model weights to their respective shards. |
| model_mtp.safetensors | Safetensors | 849 MB | Link | Multi-Token Prediction (MTP) auxiliary model weights, used to speed up generation. |
| processor_config.json | JSON | 1.22 kB | Link | Configuration for the multimodal processor. |
| recipe.yaml | YAML | 334 Bytes | Link | Configuration file detailing the quantization or training recipe (e.g., NVFP4 parameters). |
| tokenizer.json | JSON | 20 MB | Link | Complete tokenizer vocabulary and encoding rules. |
| tokenizer_config.json | JSON | 1.22 kB | Link | Tokenizer-specific configuration parameters. |