Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,27 +1,113 @@
 {
-  "model_type": "privacy_filter",
-  "inference_contract_version": 1,
-  "encoding": "o200k_base",
-  "num_hidden_layers": 8,
-  "num_experts": 128,
-  "experts_per_token": 4,
-  "vocab_size": 200064,
-  "num_labels": 33,
+  "architectures": [
+    "OpenAIPrivacyFilterForTokenClassification"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_dropout": 0.0,
+  "default_n_ctx": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 199999,
+  "head_dim": 64,
+  "hidden_act": "silu",
   "hidden_size": 640,
+  "id2label": {
+    "0": "O",
+    "1": "B-account_number",
+    "2": "I-account_number",
+    "3": "E-account_number",
+    "4": "S-account_number",
+    "5": "B-private_address",
+    "6": "I-private_address",
+    "7": "E-private_address",
+    "8": "S-private_address",
+    "9": "B-private_date",
+    "10": "I-private_date",
+    "11": "E-private_date",
+    "12": "S-private_date",
+    "13": "B-private_email",
+    "14": "I-private_email",
+    "15": "E-private_email",
+    "16": "S-private_email",
+    "17": "B-private_person",
+    "18": "I-private_person",
+    "19": "E-private_person",
+    "20": "S-private_person",
+    "21": "B-private_phone",
+    "22": "I-private_phone",
+    "23": "E-private_phone",
+    "24": "S-private_phone",
+    "25": "B-private_url",
+    "26": "I-private_url",
+    "27": "E-private_url",
+    "28": "S-private_url",
+    "29": "B-secret",
+    "30": "I-secret",
+    "31": "E-secret",
+    "32": "S-secret"
+  },
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
   "intermediate_size": 640,
-  "head_dim": 64,
+  "label2id": {
+    "B-account_number": 1,
+    "B-private_address": 5,
+    "B-private_date": 9,
+    "B-private_email": 13,
+    "B-private_person": 17,
+    "B-private_phone": 21,
+    "B-private_url": 25,
+    "B-secret": 29,
+    "E-account_number": 3,
+    "E-private_address": 7,
+    "E-private_date": 11,
+    "E-private_email": 15,
+    "E-private_person": 19,
+    "E-private_phone": 23,
+    "E-private_url": 27,
+    "E-secret": 31,
+    "I-account_number": 2,
+    "I-private_address": 6,
+    "I-private_date": 10,
+    "I-private_email": 14,
+    "I-private_person": 18,
+    "I-private_phone": 22,
+    "I-private_url": 26,
+    "I-secret": 30,
+    "O": 0,
+    "S-account_number": 4,
+    "S-private_address": 8,
+    "S-private_date": 12,
+    "S-private_email": 16,
+    "S-private_person": 20,
+    "S-private_phone": 24,
+    "S-private_url": 28,
+    "S-secret": 32
+  },
+  "max_position_embeddings": 131072,
+  "model_type": "openai_privacy_filter",
   "num_attention_heads": 14,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 8,
   "num_key_value_heads": 2,
-  "sliding_window": 257,
-  "bidirectional_context": true,
-  "bidirectional_left_context": 128,
-  "bidirectional_right_context": 128,
-  "initial_context_length": 4096,
-  "max_position_embeddings": 131072,
-  "default_n_ctx": 128000,
-  "rope_theta": 150000,
-  "rope_scaling_factor": 32.0,
-  "rope_ntk_alpha": 1.0,
-  "rope_ntk_beta": 32.0,
-  "param_dtype": "bfloat16"
-}
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_theta": 150000.0,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": 128,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0.dev0",
+  "use_cache": true,
+  "vocab_size": 200064
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c262cbe68a0c8a50590a648ef8341a2b7d3be1fa11dfb79893fe0b03ce57b5c
-size 2798984088
+oid sha256:06f66b87650b988b04e218285f9fe3df6a4943416b6ffa8171f07bc56cf12a9d
+size 2798989498

model.sig

@@ -0,0 +1 @@
+{"mediaType":"application/vnd.dev.sigstore.bundle.v0.3+json","verificationMaterial":{"certificate":{"rawBytes":"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"},"tlogEntries":[{"logIndex":"1354612699","logId":{"keyId":"wNI9atQGlz+VWfO6LRygH4QUfY/8W4RFwiT5i5WRgB0="},"kindVersion":{"kind":"dsse","version":"0.0.1"},"integratedTime":"1776808796","inclusionPromise":{"signedEntryTimestamp":"MEUCIQCA+GtGjyeRGzU7S5gOQUzexSJ2/nhBFwPSosJOELg2ewIgTc74rmV3jNul/o2Kw+OwZ3TzPOnaHzkT0EOocIAeSOA="},"inclusionProof":{"logIndex":"1232708437","rootHash":"nchgi24x7O/+YiG9hlvttKt2W8pqpy3OWMN/p69EIDA=","treeSize":"1232708448","hashes":["xwHuQsLbdQF7RIVZq5+w5kN5xur+L0w77q29mNAdoRs=","1GjkCkuFNkSEEBQ34X/49pIGmzY3kTta4MujeTMOqBQ=","Y2lTuVU+YCsw0kt7WwOCBTpk+Ttf7euP1/wJy6aHVbk=","z1aAOTH8ddS6GmYoXOW+EynGK7EYX/2veyCWuPr0C2c=","pRt4yhKjO4bntplQg/UarNBov1jDtxxu5BVgK/mrcgo=","H38GItgBmux3iI/axwlzXJV2aBIIgRrvQiYx7gAQHc8=","pwLc6AtQt7f2YRsB7sjUvpJFEXrgxDsPudqW0rS/ubw=","K3r6pB8soELQjr1Sj47DFKNl8liPwOSlwtaxSQMAVog=","tPsqJG3nuDH0c9z/VD3f2P4qX/NOaSHzqoTsqgtSIaE=","UncvKzB/Fwgn9LZX2C6hMNHC8iPn4tmSL5keawb6NX4=","zxphkNZ9duIJ/iIXhJHDkEaxlNa/CmaTH1CpIoWE3c8=","Ln3xZzBGkHtogF9TnfaNTUIqK1s5cSzsleBENXPMnv8=","iobzhDrEkM0vZcqzFqeHCrSQahM3UpIbm/nQjybM6t4=","gMqcPcRZq+qRpt2j2OrT6TYi0jJLQuxyfSCsDoyUYec=","7VGyDu6EqZ3w6qHPrlqezexOYVPJMZym3mFk1ula7AQ=","rHnyNltMkQ8pSBC0fcmsZJct4w7xKTvfhytE5NXvQMM=","7y22/OdvnNTJ3gzz57WEW6D/mmmrLXV0dVQyDwenx5A=","DOCeoSMovIvLExkhIvisow9AuNXgeWs4ECkyR6EcqYU="],"checkpoint":{"envelope":"rekor.sigstore.dev - 1193050959916656506\n1232708448\nnchgi24x7O/+YiG9hlvttKt2W8pqpy3OWMN/p69EIDA=\n\n— rekor.sigstore.dev wNI9ajBFAiB0ZQSCs34b7xviY2c51l1PmK5o+DKLdH5vczDM+UQtggIhAPB/q2z9/7NIZ0Lbty0GUAZ8kaMHmhVOlAL6XzsrtmjY\n"}},"canonicalizedBody":"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"}],"timestampVerificationData":{"rfc3161Timestamps":[{"signedTimestamp":"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"}]}},"dsseEnvelope":{"payload":"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","payloadType":"application/vnd.in-toto+json","signatures":[{"sig":"MEQCIFbKtHFWXrhgKbGefty115qYYNb+eb/1yc/sSlAJ5uN8AiAwa8rLBH61sSA7NTLsfse4IF8bCk5UWVNRQ4QuSTac6A=="}]}}

original/config.json

@@ -0,0 +1,27 @@
+{
+  "model_type": "privacy_filter",
+  "inference_contract_version": 1,
+  "encoding": "o200k_base",
+  "num_hidden_layers": 8,
+  "num_experts": 128,
+  "experts_per_token": 4,
+  "vocab_size": 200064,
+  "num_labels": 33,
+  "hidden_size": 640,
+  "intermediate_size": 640,
+  "head_dim": 64,
+  "num_attention_heads": 14,
+  "num_key_value_heads": 2,
+  "sliding_window": 257,
+  "bidirectional_context": true,
+  "bidirectional_left_context": 128,
+  "bidirectional_right_context": 128,
+  "initial_context_length": 4096,
+  "max_position_embeddings": 131072,
+  "default_n_ctx": 128000,
+  "rope_theta": 150000,
+  "rope_scaling_factor": 32.0,
+  "rope_ntk_alpha": 1.0,
+  "rope_ntk_beta": 32.0,
+  "param_dtype": "bfloat16"
+}

original/dtypes.json

@@ -0,0 +1,92 @@
+{
+  "embedding.weight": "torch.bfloat16",
+  "block.0.attn.qkv.weight": "torch.bfloat16",
+  "block.0.attn.qkv.bias": "torch.bfloat16",
+  "block.0.attn.sinks": "torch.float32",
+  "block.0.attn.out.weight": "torch.bfloat16",
+  "block.0.attn.out.bias": "torch.bfloat16",
+  "block.0.mlp.gate.weight": "torch.bfloat16",
+  "block.0.mlp.gate.bias": "torch.bfloat16",
+  "block.0.mlp.swiglu.weight": "torch.bfloat16",
+  "block.0.mlp.swiglu.bias": "torch.bfloat16",
+  "block.0.mlp.out.weight": "torch.bfloat16",
+  "block.0.mlp.out.bias": "torch.bfloat16",
+  "block.1.attn.qkv.weight": "torch.bfloat16",
+  "block.1.attn.qkv.bias": "torch.bfloat16",
+  "block.1.attn.sinks": "torch.float32",
+  "block.1.attn.out.weight": "torch.bfloat16",
+  "block.1.attn.out.bias": "torch.bfloat16",
+  "block.1.mlp.gate.weight": "torch.bfloat16",
+  "block.1.mlp.gate.bias": "torch.bfloat16",
+  "block.1.mlp.swiglu.weight": "torch.bfloat16",
+  "block.1.mlp.swiglu.bias": "torch.bfloat16",
+  "block.1.mlp.out.weight": "torch.bfloat16",
+  "block.1.mlp.out.bias": "torch.bfloat16",
+  "block.2.attn.qkv.weight": "torch.bfloat16",
+  "block.2.attn.qkv.bias": "torch.bfloat16",
+  "block.2.attn.sinks": "torch.float32",
+  "block.2.attn.out.weight": "torch.bfloat16",
+  "block.2.attn.out.bias": "torch.bfloat16",
+  "block.2.mlp.gate.weight": "torch.bfloat16",
+  "block.2.mlp.gate.bias": "torch.bfloat16",
+  "block.2.mlp.swiglu.weight": "torch.bfloat16",
+  "block.2.mlp.swiglu.bias": "torch.bfloat16",
+  "block.2.mlp.out.weight": "torch.bfloat16",
+  "block.2.mlp.out.bias": "torch.bfloat16",
+  "block.3.attn.qkv.weight": "torch.bfloat16",
+  "block.3.attn.qkv.bias": "torch.bfloat16",
+  "block.3.attn.sinks": "torch.float32",
+  "block.3.attn.out.weight": "torch.bfloat16",
+  "block.3.attn.out.bias": "torch.bfloat16",
+  "block.3.mlp.gate.weight": "torch.bfloat16",
+  "block.3.mlp.gate.bias": "torch.bfloat16",
+  "block.3.mlp.swiglu.weight": "torch.bfloat16",
+  "block.3.mlp.swiglu.bias": "torch.bfloat16",
+  "block.3.mlp.out.weight": "torch.bfloat16",
+  "block.3.mlp.out.bias": "torch.bfloat16",
+  "block.4.attn.qkv.weight": "torch.bfloat16",
+  "block.4.attn.qkv.bias": "torch.bfloat16",
+  "block.4.attn.sinks": "torch.float32",
+  "block.4.attn.out.weight": "torch.bfloat16",
+  "block.4.attn.out.bias": "torch.bfloat16",
+  "block.4.mlp.gate.weight": "torch.bfloat16",
+  "block.4.mlp.gate.bias": "torch.bfloat16",
+  "block.4.mlp.swiglu.weight": "torch.bfloat16",
+  "block.4.mlp.swiglu.bias": "torch.bfloat16",
+  "block.4.mlp.out.weight": "torch.bfloat16",
+  "block.4.mlp.out.bias": "torch.bfloat16",
+  "block.5.attn.qkv.weight": "torch.bfloat16",
+  "block.5.attn.qkv.bias": "torch.bfloat16",
+  "block.5.attn.sinks": "torch.float32",
+  "block.5.attn.out.weight": "torch.bfloat16",
+  "block.5.attn.out.bias": "torch.bfloat16",
+  "block.5.mlp.gate.weight": "torch.bfloat16",
+  "block.5.mlp.gate.bias": "torch.bfloat16",
+  "block.5.mlp.swiglu.weight": "torch.bfloat16",
+  "block.5.mlp.swiglu.bias": "torch.bfloat16",
+  "block.5.mlp.out.weight": "torch.bfloat16",
+  "block.5.mlp.out.bias": "torch.bfloat16",
+  "block.6.attn.qkv.weight": "torch.bfloat16",
+  "block.6.attn.qkv.bias": "torch.bfloat16",
+  "block.6.attn.sinks": "torch.float32",
+  "block.6.attn.out.weight": "torch.bfloat16",
+  "block.6.attn.out.bias": "torch.bfloat16",
+  "block.6.mlp.gate.weight": "torch.bfloat16",
+  "block.6.mlp.gate.bias": "torch.bfloat16",
+  "block.6.mlp.swiglu.weight": "torch.bfloat16",
+  "block.6.mlp.swiglu.bias": "torch.bfloat16",
+  "block.6.mlp.out.weight": "torch.bfloat16",
+  "block.6.mlp.out.bias": "torch.bfloat16",
+  "block.7.attn.qkv.weight": "torch.bfloat16",
+  "block.7.attn.qkv.bias": "torch.bfloat16",
+  "block.7.attn.sinks": "torch.float32",
+  "block.7.attn.out.weight": "torch.bfloat16",
+  "block.7.attn.out.bias": "torch.bfloat16",
+  "block.7.mlp.gate.weight": "torch.bfloat16",
+  "block.7.mlp.gate.bias": "torch.bfloat16",
+  "block.7.mlp.swiglu.weight": "torch.bfloat16",
+  "block.7.mlp.swiglu.bias": "torch.bfloat16",
+  "block.7.mlp.out.weight": "torch.bfloat16",
+  "block.7.mlp.out.bias": "torch.bfloat16",
+  "unembedding.weight": "torch.bfloat16"
+}

original/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c262cbe68a0c8a50590a648ef8341a2b7d3be1fa11dfb79893fe0b03ce57b5c
+size 2798984088

original/viterbi_calibration.json

@@ -0,0 +1,14 @@
+{
+  "operating_points": {
+    "default": {
+      "biases": {
+        "transition_bias_background_stay": 0.0,
+        "transition_bias_background_to_start": 0.0,
+        "transition_bias_end_to_background": 0.0,
+        "transition_bias_end_to_start": 0.0,
+        "transition_bias_inside_to_continue": 0.0,
+        "transition_bias_inside_to_end": 0.0
+      }
+    }
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
+size 27868174

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend"
+}