| { | |
| "_name_or_path": "/root/.cache/huggingface/hub/models--KingNish--Reasoning-0.5b/snapshots/fca9019dec693bfcb8a1fbc39e301636ae2c518d", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 151643, | |
| "quantization_config": { | |
| "quant_method": "compressed-tensors", | |
| "sparsity_config": { | |
| "format": "sparse-bitmask", | |
| "global_sparsity": 0.28391460298652316, | |
| "ignore": [ | |
| "lm_head" | |
| ], | |
| "registry_requires_subclass": false, | |
| "sparsity_structure": "2:4", | |
| "targets": [ | |
| "Linear" | |
| ] | |
| }, | |
| "version": "0.7.1.20241105" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.46.2", | |
| "unsloth_version": "2024.9.post4", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } |