File size: 1,414 Bytes
ad6960f |
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 |
{
"architectures": [
"Gemma3ForConditionalGeneration"
],
"boi_token_index": 255999,
"eoi_token_index": 256000,
"eos_token_id": [
1,
106
],
"image_token_index": 262144,
"initializer_range": 0.02,
"mm_tokens_per_image": 256,
"model_type": "gemma3",
"text_config": {
"hidden_size": 2560,
"intermediate_size": 10240,
"model_type": "gemma3_text",
"num_hidden_layers": 34,
"rope_scaling": {
"factor": 8.0,
"rope_type": "linear"
},
"sliding_window": 1024
},
"torch_dtype": "bfloat16",
"transformers_version": "4.50.0.dev0",
"vision_config": {
"hidden_size": 1152,
"image_size": 896,
"intermediate_size": 4304,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 27,
"patch_size": 14,
"vision_use_head": false
},
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": null,
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"group_size": 32,
"num_bits": 4,
"strategy": "group",
"symmetric": true,
"type": "int"
}
}
},
"format": "pack-quantized",
"ignore": [
"lm_head",
"re:vision_tower.*"
],
"quant_method": "compressed-tensors",
"quantization_status": "compressed"
}
}
|