Instructions to use nvidia/AceMath-72B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
Download config.json from nvidia/AceMath-72B-Instruct: direct link, hf CLI and curl.
- Browser
- Download file 678 Bytes
-
https://huggingface.co/nvidia/AceMath-72B-Instruct/resolve/main/config.json
- Command line
-
hf download hf://nvidia/AceMath-72B-Instruct/config.json
-
curl -L -o config.json https://huggingface.co/nvidia/AceMath-72B-Instruct/resolve/main/config.json
678 Bytes
| { | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 29568, | |
| "max_position_embeddings": 4096, | |
| "max_window_layers": 28, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.44.0", | |
| "use_cache": true, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } | |