File size: 2,395 Bytes
c8f99ca f718275 cdb28d2 c8f99ca cdb28d2 f718275 cdb28d2 c8f99ca cdb28d2 f718275 cdb28d2 c8f99ca cdb28d2 c8f99ca cdb28d2 c8f99ca cdb28d2 f718275 cdb28d2 f718275 cdb28d2 c8f99ca cdb28d2 c8f99ca |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 25600,
"max_position_embeddings": 40960,
"max_window_layers": 64,
"model_type": "qwen3",
"num_attention_heads": 64,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": 151654,
"quantization_config": {
"_load_in_4bit": true,
"_load_in_8bit": false,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_storage": "uint8",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": [
"lm_head",
"multi_modal_projector",
"merger",
"modality_projection",
"model.layers.54.mlp",
"model.layers.50.mlp",
"model.layers.23.mlp",
"model.layers.46.mlp",
"model.layers.49.mlp",
"model.layers.48.mlp",
"model.layers.47.mlp",
"model.layers.51.mlp",
"model.layers.44.mlp",
"model.layers.52.mlp",
"model.layers.53.mlp",
"model.layers.43.mlp",
"model.layers.24.mlp",
"model.layers.41.mlp",
"model.layers.45.mlp",
"model.layers.42.mlp",
"model.layers.39.mlp",
"model.layers.40.mlp",
"model.layers.34.mlp",
"model.layers.27.mlp",
"model.layers.37.mlp",
"model.layers.25.mlp",
"model.layers.30.mlp",
"model.layers.33.mlp",
"model.layers.26.mlp",
"model.layers.38.mlp",
"model.layers.35.mlp",
"model.layers.36.mlp",
"model.layers.31.mlp",
"model.layers.32.mlp",
"model.layers.28.mlp",
"model.layers.29.mlp",
"model.layers.62.mlp",
"model.layers.6.mlp",
"model.layers.7.mlp.down_proj",
"model.layers.45.self_attn.o_proj"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"unsloth_fixed": true,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}
|