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

@@ -0,0 +1,157 @@
+{
+    "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,
+    "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,
+    "num_local_experts": 128,
+    "output_router_logits": false,
+    "pad_token_id": 199999,
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "mode": "affine",
+        "model.layers.0.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.router": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "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.js_config": {
+        "use_external_data_format": {
+            "model.onnx": 3,
+            "model_fp16.onnx": 2,
+            "model": 1
+        }
+    },
+    "transformers_version": "5.6.0.dev0",
+    "use_cache": true,
+    "vocab_size": 200064
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efc7a5da29b8b7dfef7997d5015b7d238967e2ba5e8435b4e9b5282fae24d02d
+size 1488854995

model.safetensors.index.json

@@ -0,0 +1,295 @@
+{
+    "metadata": {
+        "total_size": 1488822730
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.0.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.0.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.0.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.router.bias": "model.safetensors",
+        "model.layers.0.mlp.router.biases": "model.safetensors",
+        "model.layers.0.mlp.router.scales": "model.safetensors",
+        "model.layers.0.mlp.router.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.sinks": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.1.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.1.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.1.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.router.bias": "model.safetensors",
+        "model.layers.1.mlp.router.biases": "model.safetensors",
+        "model.layers.1.mlp.router.scales": "model.safetensors",
+        "model.layers.1.mlp.router.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.sinks": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.2.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.2.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.2.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.router.bias": "model.safetensors",
+        "model.layers.2.mlp.router.biases": "model.safetensors",
+        "model.layers.2.mlp.router.scales": "model.safetensors",
+        "model.layers.2.mlp.router.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.sinks": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.3.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.3.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.3.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.router.bias": "model.safetensors",
+        "model.layers.3.mlp.router.biases": "model.safetensors",
+        "model.layers.3.mlp.router.scales": "model.safetensors",
+        "model.layers.3.mlp.router.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.sinks": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.4.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.4.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.4.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.router.bias": "model.safetensors",
+        "model.layers.4.mlp.router.biases": "model.safetensors",
+        "model.layers.4.mlp.router.scales": "model.safetensors",
+        "model.layers.4.mlp.router.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.sinks": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.5.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.5.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.5.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.router.bias": "model.safetensors",
+        "model.layers.5.mlp.router.biases": "model.safetensors",
+        "model.layers.5.mlp.router.scales": "model.safetensors",
+        "model.layers.5.mlp.router.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.sinks": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.6.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.6.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.6.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.router.bias": "model.safetensors",
+        "model.layers.6.mlp.router.biases": "model.safetensors",
+        "model.layers.6.mlp.router.scales": "model.safetensors",
+        "model.layers.6.mlp.router.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.sinks": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.experts.down_proj.bias": "model.safetensors",
+        "model.layers.7.mlp.experts.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.experts.down_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.experts.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.experts.gate_proj.bias": "model.safetensors",
+        "model.layers.7.mlp.experts.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.experts.gate_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.experts.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.experts.up_proj.bias": "model.safetensors",
+        "model.layers.7.mlp.experts.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.experts.up_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.experts.up_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.router.bias": "model.safetensors",
+        "model.layers.7.mlp.router.biases": "model.safetensors",
+        "model.layers.7.mlp.router.scales": "model.safetensors",
+        "model.layers.7.mlp.router.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.sinks": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors",
+        "score.bias": "model.safetensors",
+        "score.biases": "model.safetensors",
+        "score.scales": "model.safetensors",
+        "score.weight": "model.safetensors"
+    }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "<|endoftext|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend"
+}

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
+      }
+    }
+  }
+}