RasmusVeski/MNLP_M3_quantized_model_bitsandbytes4bit_16ac_nested
015
1{2 "architectures": [3 "Qwen3ForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 151643,8 "eos_token_id": 151643,9 "head_dim": 128,10 "hidden_act": "silu",11 "hidden_size": 1024,12 "initializer_range": 0.02,13 "intermediate_size": 3072,14 "max_position_embeddings": 32768,15 "max_window_layers": 28,16 "model_type": "qwen3",17 "num_attention_heads": 16,18 "num_hidden_layers": 28,19 "num_key_value_heads": 8,20 "pad_token_id": 151643,21 "quantization_config": {22 "_load_in_4bit": true,23 "_load_in_8bit": false,24 "bnb_4bit_compute_dtype": "bfloat16",25 "bnb_4bit_quant_storage": "uint8",26 "bnb_4bit_quant_type": "nf4",27 "bnb_4bit_use_double_quant": true,28 "llm_int8_enable_fp32_cpu_offload": false,29 "llm_int8_has_fp16_weight": false,30 "llm_int8_skip_modules": null,31 "llm_int8_threshold": 6.0,32 "load_in_4bit": true,33 "load_in_8bit": false,34 "quant_method": "bitsandbytes"35 },36 "rms_norm_eps": 1e-06,37 "rope_scaling": null,38 "rope_theta": 1000000,39 "sliding_window": null,40 "tie_word_embeddings": true,41 "torch_dtype": "float16",42 "transformers_version": "4.51.3",43 "use_cache": true,44 "use_sliding_window": false,45 "vocab_size": 15193646}47 