| { |
| "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", |
| "architectures": [ |
| "Qwen2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 151646, |
| "eos_token_id": 151643, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 13824, |
| "max_position_embeddings": 131072, |
| "max_window_layers": 48, |
| "model_type": "qwen2", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 48, |
| "num_key_value_heads": 8, |
| "pad_token_id": 151654, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.49.0.dev0", |
| "unsloth_fixed": true, |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 152064, |
| "quantization_config": { |
| "global_quant_config": { |
| "input_tensors": null, |
| "output_tensors": null, |
| "weight": { |
| "dtype": "fp8_e4m3", |
| "is_dynamic": false, |
| "qscheme": "per_channel", |
| "ch_axis": 0, |
| "group_size": null, |
| "block_size": null, |
| "symmetric": true, |
| "round_method": "half_even", |
| "scale_type": "float", |
| "scale_format": null, |
| "scale_calculation_mode": null, |
| "mx_element_dtype": null, |
| "observer_cls": "PerChannelMinMaxObserver", |
| "is_scale_quant": false, |
| "enable_buffer_reuse": false, |
| "max_input_numel": 4194304 |
| }, |
| "bias": null, |
| "target_device": null |
| }, |
| "exclude": [ |
| "lm_head" |
| ], |
| "algo_config": null, |
| "softmax_quant_spec": null, |
| "quant_method": "fp8", |
| "layer_type_quant_config": {}, |
| "layer_quant_config": {}, |
| "kv_cache_quant_config": {}, |
| "kv_cache_post_rope": false, |
| "quant_mode": "eager_mode", |
| "version": "0.12.post1", |
| "export": { |
| "kv_cache_group": [], |
| "min_kv_scale": 0.0, |
| "pack_method": "reorder", |
| "weight_format": "real_quantized", |
| "weight_merge_groups": null |
| } |
| } |
| } |
