upload model_config.json
Browse files- model_config.json +98 -0
model_config.json
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "embeddinggemma-300m",
|
| 3 |
+
"architecture": "gemma3-embedding",
|
| 4 |
+
"tokenizer_repo": "google/embeddinggemma-300m",
|
| 5 |
+
"parts": {
|
| 6 |
+
"encoder": "encoder.mlpackage"
|
| 7 |
+
},
|
| 8 |
+
"io_contract": {
|
| 9 |
+
"inputs": {
|
| 10 |
+
"input_ids": {
|
| 11 |
+
"shape": [
|
| 12 |
+
1,
|
| 13 |
+
128
|
| 14 |
+
],
|
| 15 |
+
"dtype": "int32"
|
| 16 |
+
},
|
| 17 |
+
"attention_mask": {
|
| 18 |
+
"shape": [
|
| 19 |
+
1,
|
| 20 |
+
128
|
| 21 |
+
],
|
| 22 |
+
"dtype": "fp16",
|
| 23 |
+
"doc": "1.0 for valid tokens, 0.0 for pad"
|
| 24 |
+
}
|
| 25 |
+
},
|
| 26 |
+
"outputs": {
|
| 27 |
+
"embedding": {
|
| 28 |
+
"shape": [
|
| 29 |
+
1,
|
| 30 |
+
768
|
| 31 |
+
],
|
| 32 |
+
"dtype": "fp16",
|
| 33 |
+
"doc": "L2-normalized; Matryoshka-truncate the last dim"
|
| 34 |
+
}
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"hidden_size": 768,
|
| 38 |
+
"num_hidden_layers": 24,
|
| 39 |
+
"num_attention_heads": 3,
|
| 40 |
+
"num_key_value_heads": 1,
|
| 41 |
+
"head_dim": 256,
|
| 42 |
+
"intermediate_size": 1152,
|
| 43 |
+
"vocab_size": 262144,
|
| 44 |
+
"max_seq_len": 128,
|
| 45 |
+
"sliding_window": 512,
|
| 46 |
+
"sliding_window_pattern": 6,
|
| 47 |
+
"layer_types": [
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"sliding_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"sliding_attention",
|
| 55 |
+
"sliding_attention",
|
| 56 |
+
"sliding_attention",
|
| 57 |
+
"sliding_attention",
|
| 58 |
+
"sliding_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"sliding_attention",
|
| 61 |
+
"sliding_attention",
|
| 62 |
+
"sliding_attention",
|
| 63 |
+
"sliding_attention",
|
| 64 |
+
"sliding_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"sliding_attention",
|
| 67 |
+
"sliding_attention",
|
| 68 |
+
"sliding_attention",
|
| 69 |
+
"sliding_attention",
|
| 70 |
+
"sliding_attention",
|
| 71 |
+
"full_attention"
|
| 72 |
+
],
|
| 73 |
+
"rms_norm_eps": 1e-06,
|
| 74 |
+
"rope_theta_global": 1000000.0,
|
| 75 |
+
"rope_theta_local": 10000.0,
|
| 76 |
+
"embed_dim": 768,
|
| 77 |
+
"dense_intermediate_dim": 3072,
|
| 78 |
+
"pooling": "mean",
|
| 79 |
+
"normalize": "l2",
|
| 80 |
+
"matryoshka_dims": [
|
| 81 |
+
768,
|
| 82 |
+
512,
|
| 83 |
+
256,
|
| 84 |
+
128
|
| 85 |
+
],
|
| 86 |
+
"task_prefixes": {
|
| 87 |
+
"retrieval_query": "task: search result | query: ",
|
| 88 |
+
"retrieval_document": "title: none | text: ",
|
| 89 |
+
"classification": "task: classification | query: ",
|
| 90 |
+
"clustering": "task: clustering | query: ",
|
| 91 |
+
"similarity": "task: sentence similarity | query: ",
|
| 92 |
+
"code_retrieval": "task: code retrieval | query: ",
|
| 93 |
+
"question_answering": "task: question answering | query: ",
|
| 94 |
+
"fact_verification": "task: fact checking | query: "
|
| 95 |
+
},
|
| 96 |
+
"quantization": "fp16",
|
| 97 |
+
"compute_units": "CPU_AND_NE"
|
| 98 |
+
}
|