Mike0021 commited on
Commit
e4ab6c6
·
verified ·
1 Parent(s): 7c7dfe8

Add MLX conversion artifacts

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ pulpie-orange.png filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,214 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ library_name: mlx
4
+ pipeline_tag: token-classification
5
+ base_model: feyninc/pulpie-orange-small
6
+ tags:
7
+ - mlx
8
+ - eurobert
9
+ - token-classification
10
+ - html
11
+ - content-extraction
12
+ - boilerplate-removal
13
+ - web-scraping
14
+ - encoder
15
+ - custom-code
16
+ ---
17
+
18
+ # Pulpie Orange Small MLX
19
+
20
+ This repository contains MLX weights for
21
+ [`feyninc/pulpie-orange-small`](https://huggingface.co/feyninc/pulpie-orange-small),
22
+ a 210M-parameter EuroBERT token-classification model for main-content extraction
23
+ from HTML.
24
+
25
+ The source checkpoint is an encoder-only EuroBERT model with RoPE, RMSNorm,
26
+ SwiGLU MLP layers, and a token-classification head. It is not a decoder-only
27
+ LLM, so this conversion does not use `mlx-lm`'s standard LLM model classes.
28
+ Instead, this repository includes `modeling_eurobert_mlx.py`, a small MLX
29
+ implementation of the source architecture with matching parameter names.
30
+
31
+ ## Files
32
+
33
+ | File | Purpose |
34
+ | --- | --- |
35
+ | `model-bf16.safetensors` | Native 16-bit BF16 MLX weights converted from the source checkpoint. |
36
+ | `model-8bit.safetensors` | MLX affine 8-bit weight-quantized variant. |
37
+ | `model-4bit.safetensors` | MLX affine 4-bit weight-quantized variant. |
38
+ | `modeling_eurobert_mlx.py` | MLX EuroBERT token-classification loader. |
39
+ | `mlx_config.json` | Variant metadata and quantization settings. |
40
+ | `verification_report.json` | Load, numerical, extraction, latency, and compute-cost results. |
41
+ | `scripts/convert_to_mlx.py` | Reproducible conversion script. |
42
+ | `scripts/verify_mlx.py` | Reproducible verification script. |
43
+
44
+ ## Usage
45
+
46
+ Install dependencies:
47
+
48
+ ```bash
49
+ pip install -r requirements.txt
50
+ ```
51
+
52
+ Run a forward pass:
53
+
54
+ ```python
55
+ import sys
56
+ import mlx.core as mx
57
+ from huggingface_hub import snapshot_download
58
+ from transformers import AutoTokenizer
59
+
60
+ repo_dir = snapshot_download("Mike0021/pulpie-orange-small-mlx")
61
+ sys.path.insert(0, repo_dir)
62
+
63
+ from modeling_eurobert_mlx import load_model
64
+
65
+ tokenizer = AutoTokenizer.from_pretrained(repo_dir, trust_remote_code=True)
66
+ model = load_model(repo_dir, variant="bf16") # "bf16", "8bit", or "4bit"
67
+
68
+ inputs = tokenizer(
69
+ ["<h1>Apple MLX conversion</h1><p>Main article text.</p>"],
70
+ return_tensors="np",
71
+ padding=True,
72
+ )
73
+ input_ids = mx.array(inputs["input_ids"])
74
+ attention_mask = mx.array(inputs["attention_mask"])
75
+
76
+ logits = model(input_ids, attention_mask)
77
+ mx.eval(logits)
78
+ print(logits.shape) # batch, tokens, 2
79
+ ```
80
+
81
+ Minimal Pulpie-style extraction:
82
+
83
+ ```python
84
+ import numpy as np
85
+ import mlx.core as mx
86
+ from pulpie.chunker import extract_blocks, pack_chunks, tokenize_blocks
87
+ from pulpie.model_utils import extract_item_ids, predictions_to_labels
88
+ from pulpie.reconstruct import extract_main_html
89
+ from pulpie.simplify import simplify
90
+
91
+ html = (
92
+ "<html><body><article><h1>Apple MLX conversion</h1>"
93
+ "<p>This article explains how to convert a EuroBERT content extraction "
94
+ "model to MLX format.</p></article></body></html>"
95
+ )
96
+
97
+ simplified, map_html = simplify(html)
98
+ blocks = extract_blocks(simplified)
99
+ item_ids = extract_item_ids(blocks)
100
+ sep_id = tokenizer.convert_tokens_to_ids("<|sep|>")
101
+ chunks = pack_chunks(
102
+ tokenize_blocks(blocks, tokenizer),
103
+ max_tokens=8192,
104
+ sep_token_id=sep_id,
105
+ bos_token_id=tokenizer.bos_token_id,
106
+ eos_token_id=tokenizer.eos_token_id,
107
+ )
108
+
109
+ predictions = [0] * len(blocks)
110
+ for chunk_ids, block_indices in chunks:
111
+ ids = mx.array([chunk_ids])
112
+ mask = mx.ones_like(ids)
113
+ logits = model(ids, mask)
114
+ mx.eval(logits)
115
+ logits_np = np.array(logits.astype(mx.float32))[0]
116
+ sep_positions = np.where(np.array(chunk_ids) == sep_id)[0]
117
+ preds = logits_np[sep_positions].argmax(axis=-1).tolist()
118
+ for i, block_idx in enumerate(block_indices):
119
+ predictions[block_idx] = int(preds[i])
120
+
121
+ labels = predictions_to_labels(item_ids, predictions)
122
+ print(extract_main_html(map_html, labels))
123
+ ```
124
+
125
+ ## Conversion Methodology
126
+
127
+ 1. Downloaded `feyninc/pulpie-orange-small` from the Hugging Face Hub.
128
+ 2. Inspected `config.json`, `configuration_eurobert.py`, and
129
+ `modeling_eurobert.py`.
130
+ 3. Confirmed the model is `EuroBertForTokenClassification` with 12 layers,
131
+ hidden size 768, 12 attention heads, head dim 64, max length 8192, BF16
132
+ source weights, and 2 output labels.
133
+ 4. Confirmed current MLX can be installed on Linux with `mlx[cpu]`, so no cloud
134
+ Mac was required for conversion or load verification.
135
+ 5. Implemented a custom MLX EuroBERT token-classification module with matching
136
+ state-dict keys and the source architecture behavior.
137
+ 6. Saved the BF16 MLX weights with `mlx.core.save_safetensors`.
138
+ 7. Created 8-bit and 4-bit variants with `mlx.nn.quantize`, using affine
139
+ weight quantization, group size 64, over MLX `Linear` and `Embedding`
140
+ modules.
141
+ 8. Verified each variant with `scripts/verify_mlx.py`.
142
+
143
+ ## Verification Results
144
+
145
+ Verification was run on Linux x86_64 using `mlx[cpu]`. The PyTorch reference was
146
+ the original source checkpoint loaded in float32 with eager attention. The BF16
147
+ variant is expected to have small dtype-level differences versus that float32
148
+ reference; quantized variants have larger differences.
149
+
150
+ ### Load Checks
151
+
152
+ | Variant | Load result | Test logits shape | Test logits dtype |
153
+ | --- | --- | --- | --- |
154
+ | BF16 | Pass | `[1, 3, 2]` | `mlx.core.bfloat16` |
155
+ | 8-bit | Pass | `[1, 3, 2]` | `mlx.core.bfloat16` |
156
+ | 4-bit | Pass | `[1, 3, 2]` | `mlx.core.bfloat16` |
157
+
158
+ ### Numerical Accuracy
159
+
160
+ Test inputs: `["A", "B", "C"]`, token shape `[3, 2]`.
161
+
162
+ | Variant | Max abs diff vs PyTorch fp32 | Mean abs diff | MLX CPU latency |
163
+ | --- | ---: | ---: | ---: |
164
+ | BF16 | 0.0452327728 | 0.0191817340 | 716.88 ms |
165
+ | 8-bit | 1.2797489166 | 0.5423613191 | 9380.58 ms |
166
+ | 4-bit | 2.2551989555 | 1.1897996664 | 9323.18 ms |
167
+
168
+ PyTorch fp32 eager latency on the same input was 50.09 ms on this Linux CPU.
169
+ The quantized MLX CPU path is slow on this host and should not be read as an
170
+ Apple Silicon benchmark.
171
+
172
+ ### End-to-End Extraction
173
+
174
+ Sample HTML:
175
+
176
+ ```html
177
+ <html><body><article><h1>Apple MLX conversion</h1><p>This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>
178
+ ```
179
+
180
+ Pulpie preprocessing produced 2 blocks and one 50-token chunk. All variants
181
+ loaded, classified both blocks as `main`, and reconstructed non-empty HTML.
182
+
183
+ | Variant | Predictions | Non-empty output | MLX CPU extraction latency |
184
+ | --- | --- | --- | ---: |
185
+ | BF16 | `[1, 1]` | Pass | 5469.05 ms |
186
+ | 8-bit | `[1, 1]` | Pass | 78333.61 ms |
187
+ | 4-bit | `[1, 1]` | Pass | 77852.02 ms |
188
+
189
+ Full machine-readable results are in `verification_report.json`.
190
+
191
+ ## Limitations
192
+
193
+ - This is a custom MLX encoder/token-classification implementation, not an
194
+ `mlx-lm` decoder model.
195
+ - The 8-bit and 4-bit variants are weight-only affine MLX quantizations. They
196
+ load and pass a small extraction test, but full WebMainBench quality was not
197
+ re-evaluated.
198
+ - Linux CPU quantized latency is poor in this environment. MLX is primarily
199
+ intended for Apple Silicon GPU execution.
200
+ - The source tokenizer currently emits a Transformers regex warning. The
201
+ verifier keeps the tokenizer behavior used by the published `pulpie` package
202
+ rather than changing token IDs during conversion.
203
+
204
+ ## Compute Cost
205
+
206
+ No paid cloud Mac or hosted GPU was used. Conversion and verification were done
207
+ locally on Linux x86_64 with the MLX CPU package. Incremental compute cost:
208
+ `$0.00`.
209
+
210
+ ## License
211
+
212
+ The source model weights are licensed under CC BY-NC 4.0. This converted
213
+ checkpoint follows the same non-commercial license. The included conversion and
214
+ loader code is provided for interoperability with the converted weights.
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EuroBertForTokenClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_eurobert.EuroBertConfig",
9
+ "AutoModel": "modeling_eurobert.EuroBertModel",
10
+ "AutoModelForMaskedLM": "modeling_eurobert.EuroBertForMaskedLM",
11
+ "AutoModelForPreTraining": "modeling_eurobert.EuroBertPreTrainedModel",
12
+ "AutoModelForQuestionAnswering": "modeling_eurobert.EuroBertForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "modeling_eurobert.EuroBertForSequenceClassification",
14
+ "AutoModelForTokenClassification": "modeling_eurobert.EuroBertForTokenClassification"
15
+ },
16
+ "bos_token": "<|begin_of_text|>",
17
+ "bos_token_id": 128000,
18
+ "clf_pooling": "late",
19
+ "dtype": "bfloat16",
20
+ "eos_token": "<|end_of_text|>",
21
+ "eos_token_id": 128001,
22
+ "head_dim": 64,
23
+ "hidden_act": "silu",
24
+ "hidden_dropout": 0.0,
25
+ "hidden_size": 768,
26
+ "id2label": {
27
+ "0": "LABEL_0",
28
+ "1": "LABEL_1"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "label2id": {
33
+ "LABEL_0": 0,
34
+ "LABEL_1": 1
35
+ },
36
+ "mask_token": "<|mask|>",
37
+ "mask_token_id": 128002,
38
+ "max_position_embeddings": 8192,
39
+ "mlp_bias": false,
40
+ "model_type": "eurobert",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "num_key_value_heads": 12,
44
+ "num_labels": 2,
45
+ "pad_token": "<|end_of_text|>",
46
+ "pad_token_id": 128001,
47
+ "pretraining_tp": 1,
48
+ "rms_norm_eps": 1e-05,
49
+ "rope_scaling": null,
50
+ "rope_theta": 250000,
51
+ "tie_word_embeddings": false,
52
+ "transformers_version": "4.57.6",
53
+ "use_cache": false,
54
+ "vocab_size": 128257
55
+ }
mlx_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "EuroBertForTokenClassification",
3
+ "format": "mlx",
4
+ "implementation": "modeling_eurobert_mlx.py",
5
+ "source_model": "feyninc/pulpie-orange-small",
6
+ "variants": {
7
+ "model-4bit.safetensors": {
8
+ "description": "MLX affine weight quantized 4-bit variant.",
9
+ "dtype": "quantized",
10
+ "quantization": {
11
+ "bits": 4,
12
+ "group_size": 64,
13
+ "mode": "affine"
14
+ }
15
+ },
16
+ "model-8bit.safetensors": {
17
+ "description": "MLX affine weight quantized 8-bit variant.",
18
+ "dtype": "quantized",
19
+ "quantization": {
20
+ "bits": 8,
21
+ "group_size": 64,
22
+ "mode": "affine"
23
+ }
24
+ },
25
+ "model-bf16.safetensors": {
26
+ "description": "Native 16-bit BF16 MLX weights converted from the source safetensors.",
27
+ "dtype": "bfloat16",
28
+ "quantization": null
29
+ }
30
+ }
31
+ }
model-4bit.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86db98b6dabd65c8065f1f4afb627ad4094d77ea537190ed92aa9f9aee0b617
3
+ size 119178193
model-8bit.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821f4b4012154ffbb6caa5f4e27e6b96ab593fdef21ea31afd9ae8c9cba182d9
3
+ size 225053117
model-bf16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85e0ca355b6b39e161a06e88f71bcf947cd8f67e1c6813f6d789182d24c9c61
3
+ size 423549070
modeling_eurobert_mlx.py ADDED
@@ -0,0 +1,278 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ import json
4
+ from pathlib import Path
5
+ from typing import Any, Dict, Optional, Tuple
6
+
7
+ import mlx.core as mx
8
+ import mlx.nn as nn
9
+
10
+
11
+ WEIGHT_FILES = {
12
+ "bf16": "model-bf16.safetensors",
13
+ "16bit": "model-bf16.safetensors",
14
+ "8bit": "model-8bit.safetensors",
15
+ "4bit": "model-4bit.safetensors",
16
+ }
17
+
18
+
19
+ class EuroBertConfig:
20
+ def __init__(self, **kwargs: Any):
21
+ self.vocab_size = kwargs.get("vocab_size", 128257)
22
+ self.hidden_size = kwargs.get("hidden_size", 768)
23
+ self.intermediate_size = kwargs.get("intermediate_size", 3072)
24
+ self.num_hidden_layers = kwargs.get("num_hidden_layers", 12)
25
+ self.num_attention_heads = kwargs.get("num_attention_heads", 12)
26
+ self.num_key_value_heads = kwargs.get(
27
+ "num_key_value_heads", self.num_attention_heads
28
+ )
29
+ self.head_dim = kwargs.get(
30
+ "head_dim", self.hidden_size // self.num_attention_heads
31
+ )
32
+ self.hidden_act = kwargs.get("hidden_act", "silu")
33
+ self.rms_norm_eps = kwargs.get("rms_norm_eps", 1e-5)
34
+ self.rope_theta = kwargs.get("rope_theta", 250000.0)
35
+ self.attention_bias = kwargs.get("attention_bias", False)
36
+ self.mlp_bias = kwargs.get("mlp_bias", False)
37
+ self.pad_token_id = kwargs.get("pad_token_id", 128001)
38
+ self.max_position_embeddings = kwargs.get("max_position_embeddings", 8192)
39
+ self.num_labels = kwargs.get("num_labels", len(kwargs.get("id2label", {})) or 2)
40
+ self.raw = kwargs
41
+
42
+ @classmethod
43
+ def from_json(cls, path: str | Path) -> "EuroBertConfig":
44
+ with open(path, "r", encoding="utf-8") as f:
45
+ return cls(**json.load(f))
46
+
47
+
48
+ def _silu(x: mx.array) -> mx.array:
49
+ return x * mx.sigmoid(x)
50
+
51
+
52
+ def _rotate_half(x: mx.array) -> mx.array:
53
+ x1 = x[..., : x.shape[-1] // 2]
54
+ x2 = x[..., x.shape[-1] // 2 :]
55
+ return mx.concatenate([-x2, x1], axis=-1)
56
+
57
+
58
+ def _apply_rotary_pos_emb(
59
+ q: mx.array, k: mx.array, cos: mx.array, sin: mx.array
60
+ ) -> Tuple[mx.array, mx.array]:
61
+ cos = cos[:, None, :, :]
62
+ sin = sin[:, None, :, :]
63
+ return (q * cos) + (_rotate_half(q) * sin), (k * cos) + (_rotate_half(k) * sin)
64
+
65
+
66
+ class EuroBertRotaryEmbedding(nn.Module):
67
+ def __init__(self, config: EuroBertConfig):
68
+ super().__init__()
69
+ self.head_dim = config.head_dim
70
+ self.rope_theta = config.rope_theta
71
+
72
+ def __call__(self, position_ids: mx.array, dtype: mx.Dtype) -> Tuple[mx.array, mx.array]:
73
+ steps = mx.arange(0, self.head_dim, 2).astype(mx.float32)
74
+ inv_freq = 1.0 / (self.rope_theta ** (steps / self.head_dim))
75
+ pos = position_ids.astype(mx.float32)
76
+ freqs = pos[..., None] * inv_freq[None, None, :]
77
+ emb = mx.concatenate([freqs, freqs], axis=-1)
78
+ return mx.cos(emb).astype(dtype), mx.sin(emb).astype(dtype)
79
+
80
+
81
+ class EuroBertAttention(nn.Module):
82
+ def __init__(self, config: EuroBertConfig):
83
+ super().__init__()
84
+ self.num_heads = config.num_attention_heads
85
+ self.num_key_value_heads = config.num_key_value_heads
86
+ self.num_key_value_groups = self.num_heads // self.num_key_value_heads
87
+ self.head_dim = config.head_dim
88
+ self.scaling = self.head_dim**-0.5
89
+
90
+ self.q_proj = nn.Linear(
91
+ config.hidden_size,
92
+ config.num_attention_heads * self.head_dim,
93
+ bias=config.attention_bias,
94
+ )
95
+ self.k_proj = nn.Linear(
96
+ config.hidden_size,
97
+ config.num_key_value_heads * self.head_dim,
98
+ bias=config.attention_bias,
99
+ )
100
+ self.v_proj = nn.Linear(
101
+ config.hidden_size,
102
+ config.num_key_value_heads * self.head_dim,
103
+ bias=config.attention_bias,
104
+ )
105
+ self.o_proj = nn.Linear(
106
+ config.num_attention_heads * self.head_dim,
107
+ config.hidden_size,
108
+ bias=config.attention_bias,
109
+ )
110
+
111
+ def _shape(self, x: mx.array, heads: int) -> mx.array:
112
+ batch, seq_len, _ = x.shape
113
+ x = x.reshape(batch, seq_len, heads, self.head_dim)
114
+ return mx.transpose(x, (0, 2, 1, 3))
115
+
116
+ def __call__(
117
+ self,
118
+ hidden_states: mx.array,
119
+ position_embeddings: Tuple[mx.array, mx.array],
120
+ attention_mask: Optional[mx.array],
121
+ ) -> mx.array:
122
+ batch, seq_len, _ = hidden_states.shape
123
+ q = self._shape(self.q_proj(hidden_states), self.num_heads)
124
+ k = self._shape(self.k_proj(hidden_states), self.num_key_value_heads)
125
+ v = self._shape(self.v_proj(hidden_states), self.num_key_value_heads)
126
+
127
+ cos, sin = position_embeddings
128
+ q, k = _apply_rotary_pos_emb(q, k, cos, sin)
129
+
130
+ if self.num_key_value_groups != 1:
131
+ k = mx.repeat(k, self.num_key_value_groups, axis=1)
132
+ v = mx.repeat(v, self.num_key_value_groups, axis=1)
133
+
134
+ scores = (q @ mx.transpose(k, (0, 1, 3, 2))).astype(mx.float32)
135
+ scores = scores * self.scaling
136
+ if attention_mask is not None:
137
+ scores = scores + attention_mask
138
+ probs = mx.softmax(scores, axis=-1).astype(q.dtype)
139
+ out = probs @ v
140
+ out = mx.transpose(out, (0, 2, 1, 3)).reshape(batch, seq_len, -1)
141
+ return self.o_proj(out)
142
+
143
+
144
+ class EuroBertMLP(nn.Module):
145
+ def __init__(self, config: EuroBertConfig):
146
+ super().__init__()
147
+ self.gate_proj = nn.Linear(
148
+ config.hidden_size, config.intermediate_size, bias=config.mlp_bias
149
+ )
150
+ self.up_proj = nn.Linear(
151
+ config.hidden_size, config.intermediate_size, bias=config.mlp_bias
152
+ )
153
+ self.down_proj = nn.Linear(
154
+ config.intermediate_size, config.hidden_size, bias=config.mlp_bias
155
+ )
156
+
157
+ def __call__(self, x: mx.array) -> mx.array:
158
+ return self.down_proj(_silu(self.gate_proj(x)) * self.up_proj(x))
159
+
160
+
161
+ class EuroBertDecoderLayer(nn.Module):
162
+ def __init__(self, config: EuroBertConfig):
163
+ super().__init__()
164
+ self.self_attn = EuroBertAttention(config)
165
+ self.mlp = EuroBertMLP(config)
166
+ self.input_layernorm = nn.RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
167
+ self.post_attention_layernorm = nn.RMSNorm(
168
+ config.hidden_size, eps=config.rms_norm_eps
169
+ )
170
+
171
+ def __call__(
172
+ self,
173
+ hidden_states: mx.array,
174
+ attention_mask: Optional[mx.array],
175
+ position_embeddings: Tuple[mx.array, mx.array],
176
+ ) -> mx.array:
177
+ residual = hidden_states
178
+ hidden_states = self.input_layernorm(hidden_states)
179
+ hidden_states = self.self_attn(
180
+ hidden_states, position_embeddings, attention_mask
181
+ )
182
+ hidden_states = residual + hidden_states
183
+
184
+ residual = hidden_states
185
+ hidden_states = self.post_attention_layernorm(hidden_states)
186
+ hidden_states = self.mlp(hidden_states)
187
+ return residual + hidden_states
188
+
189
+
190
+ class EuroBertModel(nn.Module):
191
+ def __init__(self, config: EuroBertConfig):
192
+ super().__init__()
193
+ self.config = config
194
+ self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size)
195
+ self.layers = [
196
+ EuroBertDecoderLayer(config) for _ in range(config.num_hidden_layers)
197
+ ]
198
+ self.norm = nn.RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
199
+ self.rotary_emb = EuroBertRotaryEmbedding(config)
200
+
201
+ def _attention_mask(self, attention_mask: Optional[mx.array]) -> Optional[mx.array]:
202
+ if attention_mask is None:
203
+ return None
204
+ keep = attention_mask.astype(mx.bool_)
205
+ mask = mx.where(keep[:, None, None, :], 0.0, mx.finfo(mx.float32).min)
206
+ return mask.astype(mx.float32)
207
+
208
+ def __call__(
209
+ self,
210
+ input_ids: mx.array,
211
+ attention_mask: Optional[mx.array] = None,
212
+ position_ids: Optional[mx.array] = None,
213
+ ) -> mx.array:
214
+ hidden_states = self.embed_tokens(input_ids)
215
+ batch, seq_len = input_ids.shape
216
+ if position_ids is None:
217
+ position_ids = mx.broadcast_to(mx.arange(seq_len)[None, :], (batch, seq_len))
218
+
219
+ mask = self._attention_mask(attention_mask)
220
+ position_embeddings = self.rotary_emb(position_ids, hidden_states.dtype)
221
+ for layer in self.layers:
222
+ hidden_states = layer(hidden_states, mask, position_embeddings)
223
+ return self.norm(hidden_states)
224
+
225
+
226
+ class EuroBertForTokenClassification(nn.Module):
227
+ def __init__(self, config: EuroBertConfig):
228
+ super().__init__()
229
+ self.config = config
230
+ self.model = EuroBertModel(config)
231
+ self.classifier = nn.Linear(config.hidden_size, config.num_labels)
232
+
233
+ def __call__(
234
+ self,
235
+ input_ids: mx.array,
236
+ attention_mask: Optional[mx.array] = None,
237
+ position_ids: Optional[mx.array] = None,
238
+ ) -> mx.array:
239
+ hidden_states = self.model(input_ids, attention_mask, position_ids)
240
+ return self.classifier(hidden_states)
241
+
242
+
243
+ def build_model(
244
+ config: EuroBertConfig | Dict[str, Any],
245
+ quantization: Optional[Dict[str, Any]] = None,
246
+ ) -> EuroBertForTokenClassification:
247
+ if isinstance(config, dict):
248
+ config = EuroBertConfig(**config)
249
+ model = EuroBertForTokenClassification(config)
250
+ if quantization:
251
+ nn.quantize(
252
+ model,
253
+ group_size=quantization.get("group_size", 64),
254
+ bits=quantization["bits"],
255
+ mode=quantization.get("mode", "affine"),
256
+ )
257
+ return model
258
+
259
+
260
+ def load_model(
261
+ model_path: str | Path,
262
+ variant: str = "bf16",
263
+ ) -> EuroBertForTokenClassification:
264
+ model_path = Path(model_path)
265
+ with open(model_path / "config.json", "r", encoding="utf-8") as f:
266
+ raw_config = json.load(f)
267
+ with open(model_path / "mlx_config.json", "r", encoding="utf-8") as f:
268
+ mlx_config = json.load(f)
269
+
270
+ variant = variant.lower()
271
+ if variant not in WEIGHT_FILES:
272
+ raise ValueError(f"Unknown variant {variant!r}; expected one of {sorted(WEIGHT_FILES)}")
273
+ weight_name = WEIGHT_FILES[variant]
274
+ quantization = mlx_config["variants"].get(weight_name, {}).get("quantization")
275
+ model = build_model(raw_config, quantization=quantization)
276
+ model.load_weights(str(model_path / weight_name))
277
+ mx.eval(model.parameters())
278
+ return model
pulpie-orange.png ADDED

Git LFS Details

  • SHA256: 98ef9bd59a98ad6fdd690e311ea7faaba65fe408317e313c7d7bbf22d7a2835d
  • Pointer size: 131 Bytes
  • Size of remote file: 112 kB
requirements.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ mlx>=0.31.2
2
+ transformers>=4.57.6
3
+ huggingface_hub>=1.0
4
+ pulpie>=0.0.2
5
+ torch
6
+ numpy
scripts/convert_to_mlx.py ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ import argparse
4
+ import json
5
+ import shutil
6
+ import sys
7
+ from pathlib import Path
8
+ from typing import Dict
9
+
10
+ import mlx.core as mx
11
+ import mlx.nn as nn
12
+ from mlx.utils import tree_flatten
13
+
14
+ REPO_ROOT = Path(__file__).resolve().parents[1]
15
+ if str(REPO_ROOT) not in sys.path:
16
+ sys.path.insert(0, str(REPO_ROOT))
17
+
18
+ from modeling_eurobert_mlx import EuroBertConfig, build_model # noqa: E402
19
+
20
+
21
+ TOKENIZER_FILES = [
22
+ "tokenizer.json",
23
+ "tokenizer_config.json",
24
+ "special_tokens_map.json",
25
+ ]
26
+
27
+
28
+ def _save_weights(path: Path, model, metadata: Dict[str, str]) -> None:
29
+ params = tree_flatten(model.parameters(), destination={})
30
+ mx.save_safetensors(str(path), params, metadata=metadata)
31
+
32
+
33
+ def _eval_model(model) -> None:
34
+ params = tree_flatten(model.parameters(), destination={})
35
+ if params:
36
+ mx.eval(*params.values())
37
+
38
+
39
+ def _load_source_config(source_dir: Path) -> dict:
40
+ with open(source_dir / "config.json", "r", encoding="utf-8") as f:
41
+ config = json.load(f)
42
+ weights = mx.load(str(source_dir / "model.safetensors"))
43
+ config["num_labels"] = int(weights["classifier.weight"].shape[0])
44
+ config.setdefault("id2label", {str(i): f"LABEL_{i}" for i in range(config["num_labels"])})
45
+ config.setdefault("label2id", {v: int(k) for k, v in config["id2label"].items()})
46
+ return config
47
+
48
+
49
+ def convert(source_dir: Path, output_dir: Path, include_4bit: bool) -> None:
50
+ source_dir = source_dir.resolve()
51
+ output_dir = output_dir.resolve()
52
+ output_dir.mkdir(parents=True, exist_ok=True)
53
+
54
+ config = _load_source_config(source_dir)
55
+ with open(output_dir / "config.json", "w", encoding="utf-8") as f:
56
+ json.dump(config, f, indent=2, sort_keys=True)
57
+ f.write("\n")
58
+
59
+ for filename in TOKENIZER_FILES:
60
+ shutil.copy2(source_dir / filename, output_dir / filename)
61
+ if (source_dir / "pulpie-orange.png").exists():
62
+ shutil.copy2(source_dir / "pulpie-orange.png", output_dir / "pulpie-orange.png")
63
+
64
+ mlx_config = {
65
+ "format": "mlx",
66
+ "source_model": "feyninc/pulpie-orange-small",
67
+ "architecture": "EuroBertForTokenClassification",
68
+ "implementation": "modeling_eurobert_mlx.py",
69
+ "variants": {
70
+ "model-bf16.safetensors": {
71
+ "dtype": "bfloat16",
72
+ "quantization": None,
73
+ "description": "Native 16-bit BF16 MLX weights converted from the source safetensors.",
74
+ }
75
+ },
76
+ }
77
+
78
+ model = build_model(EuroBertConfig(**config))
79
+ model.load_weights(str(source_dir / "model.safetensors"))
80
+ _eval_model(model)
81
+ _save_weights(
82
+ output_dir / "model-bf16.safetensors",
83
+ model,
84
+ {
85
+ "format": "mlx",
86
+ "variant": "bf16",
87
+ "source_model": "feyninc/pulpie-orange-small",
88
+ },
89
+ )
90
+
91
+ quantized_specs = [("8bit", 8)]
92
+ if include_4bit:
93
+ quantized_specs.append(("4bit", 4))
94
+
95
+ for name, bits in quantized_specs:
96
+ q_model = build_model(EuroBertConfig(**config))
97
+ q_model.load_weights(str(source_dir / "model.safetensors"))
98
+ nn.quantize(q_model, group_size=64, bits=bits, mode="affine")
99
+ _eval_model(q_model)
100
+ weight_name = f"model-{name}.safetensors"
101
+ _save_weights(
102
+ output_dir / weight_name,
103
+ q_model,
104
+ {
105
+ "format": "mlx",
106
+ "variant": name,
107
+ "source_model": "feyninc/pulpie-orange-small",
108
+ "quantization": json.dumps(
109
+ {"bits": bits, "group_size": 64, "mode": "affine"},
110
+ sort_keys=True,
111
+ ),
112
+ },
113
+ )
114
+ mlx_config["variants"][weight_name] = {
115
+ "dtype": "quantized",
116
+ "quantization": {"bits": bits, "group_size": 64, "mode": "affine"},
117
+ "description": f"MLX affine weight quantized {bits}-bit variant.",
118
+ }
119
+
120
+ with open(output_dir / "mlx_config.json", "w", encoding="utf-8") as f:
121
+ json.dump(mlx_config, f, indent=2, sort_keys=True)
122
+ f.write("\n")
123
+
124
+
125
+ def main() -> None:
126
+ parser = argparse.ArgumentParser(description="Convert Pulpie Orange Small to MLX.")
127
+ parser.add_argument("--source-dir", type=Path, default=Path("source_model"))
128
+ parser.add_argument("--output-dir", type=Path, default=Path("hf_out"))
129
+ parser.add_argument("--include-4bit", action="store_true")
130
+ args = parser.parse_args()
131
+ convert(args.source_dir, args.output_dir, include_4bit=args.include_4bit)
132
+
133
+
134
+ if __name__ == "__main__":
135
+ main()
scripts/verify_mlx.py ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from __future__ import annotations
2
+
3
+ import argparse
4
+ import json
5
+ import statistics
6
+ import sys
7
+ import time
8
+ from pathlib import Path
9
+ from typing import Any, Dict, List
10
+
11
+ import mlx.core as mx
12
+ import numpy as np
13
+ import torch
14
+ from transformers import AutoModelForTokenClassification, AutoTokenizer
15
+
16
+ REPO_ROOT = Path(__file__).resolve().parents[1]
17
+ if str(REPO_ROOT) not in sys.path:
18
+ sys.path.insert(0, str(REPO_ROOT))
19
+
20
+ from modeling_eurobert_mlx import load_model # noqa: E402
21
+
22
+
23
+ def _to_numpy(x: mx.array) -> np.ndarray:
24
+ return np.array(x.astype(mx.float32))
25
+
26
+
27
+ def _timed(fn, repeats: int = 1) -> tuple[Any, float]:
28
+ times = []
29
+ out = None
30
+ for _ in range(repeats):
31
+ start = time.perf_counter()
32
+ out = fn()
33
+ times.append((time.perf_counter() - start) * 1000.0)
34
+ return out, statistics.median(times)
35
+
36
+
37
+ def _load_tokenizer(model_dir: Path):
38
+ # Keep the same tokenizer behavior used by pulpie.Extractor and by the
39
+ # source model card. Transformers may warn about the regex; changing it
40
+ # changes token IDs relative to the published checkpoint.
41
+ tokenizer = AutoTokenizer.from_pretrained(str(model_dir), trust_remote_code=True)
42
+ if "<|sep|>" not in tokenizer.get_vocab():
43
+ tokenizer.add_special_tokens({"additional_special_tokens": ["<|sep|>"]})
44
+ return tokenizer
45
+
46
+
47
+ def run_load_checks(model_dir: Path, variants: List[str]) -> Dict[str, Any]:
48
+ results = {}
49
+ for variant in variants:
50
+ model = load_model(model_dir, variant)
51
+ input_ids = mx.array([[128000, 32, 128001]])
52
+ attention_mask = mx.array([[1, 1, 1]])
53
+ logits = model(input_ids, attention_mask)
54
+ mx.eval(logits)
55
+ results[variant] = {
56
+ "loaded": True,
57
+ "logits_shape": list(logits.shape),
58
+ "logits_dtype": str(logits.dtype),
59
+ }
60
+ return results
61
+
62
+
63
+ def run_numerical_checks(
64
+ source_dir: Path, model_dir: Path, variants: List[str]
65
+ ) -> Dict[str, Any]:
66
+ tokenizer = _load_tokenizer(model_dir)
67
+ texts = ["A", "B", "C"]
68
+ inputs = tokenizer(texts, return_tensors="pt", padding=True, truncation=True, max_length=8)
69
+
70
+ torch.set_num_threads(4)
71
+ torch_model = AutoModelForTokenClassification.from_pretrained(
72
+ str(source_dir),
73
+ trust_remote_code=True,
74
+ attn_implementation="eager",
75
+ dtype=torch.float32,
76
+ ).eval()
77
+
78
+ with torch.inference_mode():
79
+ torch_model(**inputs)
80
+ torch_logits, torch_ms = _timed(
81
+ lambda: torch_model(**inputs).logits.detach().cpu().numpy()
82
+ )
83
+
84
+ mx_inputs = {
85
+ key: mx.array(value.numpy())
86
+ for key, value in inputs.items()
87
+ if key in {"input_ids", "attention_mask"}
88
+ }
89
+ results = {
90
+ "test_inputs": texts,
91
+ "token_shape": list(inputs["input_ids"].shape),
92
+ "torch_reference": {
93
+ "dtype": "float32",
94
+ "attention": "eager",
95
+ "latency_ms": torch_ms,
96
+ },
97
+ "variants": {},
98
+ }
99
+
100
+ for variant in variants:
101
+ model = load_model(model_dir, variant)
102
+ logits = model(mx_inputs["input_ids"], mx_inputs["attention_mask"])
103
+ mx.eval(logits)
104
+ logits, mlx_ms = _timed(
105
+ lambda: _eval_logits(model, mx_inputs["input_ids"], mx_inputs["attention_mask"])
106
+ )
107
+ diff = np.abs(torch_logits - logits)
108
+ results["variants"][variant] = {
109
+ "latency_ms": mlx_ms,
110
+ "max_abs_diff": float(diff.max()),
111
+ "mean_abs_diff": float(diff.mean()),
112
+ }
113
+ return results
114
+
115
+
116
+ def _eval_logits(model, input_ids: mx.array, attention_mask: mx.array) -> np.ndarray:
117
+ logits = model(input_ids, attention_mask)
118
+ mx.eval(logits)
119
+ return _to_numpy(logits)
120
+
121
+
122
+ def run_extraction(model_dir: Path, variants: List[str]) -> Dict[str, Any]:
123
+ from pulpie.chunker import extract_blocks, pack_chunks, tokenize_blocks
124
+ from pulpie.markdown import to_markdown
125
+ from pulpie.model_utils import extract_item_ids, predictions_to_labels
126
+ from pulpie.reconstruct import extract_main_html
127
+ from pulpie.simplify import simplify
128
+
129
+ html = (
130
+ "<html><body><article><h1>Apple MLX conversion</h1>"
131
+ "<p>This article explains how to convert a EuroBERT content extraction "
132
+ "model to MLX format.</p></article></body></html>"
133
+ )
134
+ tokenizer = _load_tokenizer(model_dir)
135
+ sep_token_id = tokenizer.convert_tokens_to_ids("<|sep|>")
136
+ simplified, map_html = simplify(html)
137
+ blocks = extract_blocks(simplified)
138
+ item_ids = extract_item_ids(blocks)
139
+ chunks = pack_chunks(
140
+ tokenize_blocks(blocks, tokenizer),
141
+ max_tokens=128,
142
+ sep_token_id=sep_token_id,
143
+ bos_token_id=tokenizer.bos_token_id,
144
+ eos_token_id=tokenizer.eos_token_id,
145
+ )
146
+
147
+ results = {
148
+ "input_html": html,
149
+ "num_blocks": len(blocks),
150
+ "chunk_lengths": [len(chunk_ids) for chunk_ids, _ in chunks],
151
+ "variants": {},
152
+ }
153
+
154
+ for variant in variants:
155
+ model = load_model(model_dir, variant)
156
+ predictions = [0] * len(blocks)
157
+ start = time.perf_counter()
158
+ for chunk_ids, block_indices in chunks:
159
+ input_ids = mx.array([chunk_ids])
160
+ attention_mask = mx.ones_like(input_ids)
161
+ logits = model(input_ids, attention_mask)
162
+ mx.eval(logits)
163
+ logits_np = _to_numpy(logits)[0]
164
+ ids_np = np.array(chunk_ids)
165
+ sep_positions = np.where(ids_np == sep_token_id)[0]
166
+ preds = logits_np[sep_positions].argmax(axis=-1).tolist()
167
+ for idx, block_idx in enumerate(block_indices):
168
+ if idx < len(preds):
169
+ predictions[block_idx] = int(preds[idx])
170
+ latency_ms = (time.perf_counter() - start) * 1000.0
171
+ labels = predictions_to_labels(item_ids, predictions)
172
+ main_html = extract_main_html(map_html, labels)
173
+ markdown = to_markdown(main_html)
174
+ results["variants"][variant] = {
175
+ "latency_ms": latency_ms,
176
+ "predictions": predictions,
177
+ "labels": labels,
178
+ "html": main_html,
179
+ "markdown": markdown,
180
+ "non_empty": bool(markdown.strip() or main_html.strip()),
181
+ }
182
+ return results
183
+
184
+
185
+ def main() -> None:
186
+ parser = argparse.ArgumentParser(description="Verify converted MLX Pulpie weights.")
187
+ parser.add_argument("--source-dir", type=Path, default=Path("source_model"))
188
+ parser.add_argument("--model-dir", type=Path, default=Path("hf_out"))
189
+ parser.add_argument(
190
+ "--variants", nargs="+", default=["bf16", "8bit", "4bit"], help="Variants to verify."
191
+ )
192
+ parser.add_argument(
193
+ "--output", type=Path, default=Path("hf_out/verification_report.json")
194
+ )
195
+ args = parser.parse_args()
196
+
197
+ report = {
198
+ "source_model": "feyninc/pulpie-orange-small",
199
+ "model_dir": str(args.model_dir),
200
+ "variants": args.variants,
201
+ "load_checks": run_load_checks(args.model_dir, args.variants),
202
+ "numerical_accuracy": run_numerical_checks(
203
+ args.source_dir, args.model_dir, args.variants
204
+ ),
205
+ "end_to_end_extraction": run_extraction(args.model_dir, args.variants),
206
+ "compute": {
207
+ "environment": "Linux x86_64 CPU with mlx[cpu]; no paid cloud Mac used.",
208
+ "estimated_incremental_cost_usd": 0.0,
209
+ },
210
+ }
211
+ args.output.parent.mkdir(parents=True, exist_ok=True)
212
+ with open(args.output, "w", encoding="utf-8") as f:
213
+ json.dump(report, f, indent=2, sort_keys=True)
214
+ f.write("\n")
215
+ print(json.dumps(report, indent=2, sort_keys=True))
216
+
217
+
218
+ if __name__ == "__main__":
219
+ main()
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|sep|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<|begin_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "mask_token": {
20
+ "content": "<|mask|>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": {
27
+ "content": "<|pad|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d807a071da4bbd8144b0206722ec9f87dd91209f4526933d88448a1c88b922c9
3
+ size 17210257
tokenizer_config.json ADDED
@@ -0,0 +1,2079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|mask|>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|parallel_sep|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|pad|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|sep|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|sep|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "clean_up_tokenization_spaces": true,
2065
+ "eos_token": "<|end_of_text|>",
2066
+ "extra_special_tokens": {},
2067
+ "mask_token": "<|mask|>",
2068
+ "max_length": null,
2069
+ "model_input_names": [
2070
+ "input_ids",
2071
+ "attention_mask"
2072
+ ],
2073
+ "model_max_length": 1000000000000000019884624838656,
2074
+ "pad_to_multiple_of": null,
2075
+ "pad_token": "<|pad|>",
2076
+ "pad_token_type_id": 0,
2077
+ "padding_side": "right",
2078
+ "tokenizer_class": "PreTrainedTokenizerFast"
2079
+ }
verification_report.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "compute": {
3
+ "environment": "Linux x86_64 CPU with mlx[cpu]; no paid cloud Mac used.",
4
+ "estimated_incremental_cost_usd": 0.0
5
+ },
6
+ "end_to_end_extraction": {
7
+ "chunk_lengths": [
8
+ 50
9
+ ],
10
+ "input_html": "<html><body><article><h1>Apple MLX conversion</h1><p>This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>",
11
+ "num_blocks": 2,
12
+ "variants": {
13
+ "4bit": {
14
+ "html": "<html><body><article><h1 _item_id=\"1\">Apple MLX conversion</h1><p _item_id=\"2\">This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>",
15
+ "labels": {
16
+ "1": "main",
17
+ "2": "main"
18
+ },
19
+ "latency_ms": 77852.023473999,
20
+ "markdown": "<html><body><article><h1 _item_id=\"1\">Apple MLX conversion</h1><p _item_id=\"2\">This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>",
21
+ "non_empty": true,
22
+ "predictions": [
23
+ 1,
24
+ 1
25
+ ]
26
+ },
27
+ "8bit": {
28
+ "html": "<html><body><article><h1 _item_id=\"1\">Apple MLX conversion</h1><p _item_id=\"2\">This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>",
29
+ "labels": {
30
+ "1": "main",
31
+ "2": "main"
32
+ },
33
+ "latency_ms": 78333.6143399938,
34
+ "markdown": "<html><body><article><h1 _item_id=\"1\">Apple MLX conversion</h1><p _item_id=\"2\">This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>",
35
+ "non_empty": true,
36
+ "predictions": [
37
+ 1,
38
+ 1
39
+ ]
40
+ },
41
+ "bf16": {
42
+ "html": "<html><body><article><h1 _item_id=\"1\">Apple MLX conversion</h1><p _item_id=\"2\">This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>",
43
+ "labels": {
44
+ "1": "main",
45
+ "2": "main"
46
+ },
47
+ "latency_ms": 5469.0545329940505,
48
+ "markdown": "<html><body><article><h1 _item_id=\"1\">Apple MLX conversion</h1><p _item_id=\"2\">This article explains how to convert a EuroBERT content extraction model to MLX format.</p></article></body></html>",
49
+ "non_empty": true,
50
+ "predictions": [
51
+ 1,
52
+ 1
53
+ ]
54
+ }
55
+ }
56
+ },
57
+ "load_checks": {
58
+ "4bit": {
59
+ "loaded": true,
60
+ "logits_dtype": "mlx.core.bfloat16",
61
+ "logits_shape": [
62
+ 1,
63
+ 3,
64
+ 2
65
+ ]
66
+ },
67
+ "8bit": {
68
+ "loaded": true,
69
+ "logits_dtype": "mlx.core.bfloat16",
70
+ "logits_shape": [
71
+ 1,
72
+ 3,
73
+ 2
74
+ ]
75
+ },
76
+ "bf16": {
77
+ "loaded": true,
78
+ "logits_dtype": "mlx.core.bfloat16",
79
+ "logits_shape": [
80
+ 1,
81
+ 3,
82
+ 2
83
+ ]
84
+ }
85
+ },
86
+ "model_dir": "hf_out",
87
+ "numerical_accuracy": {
88
+ "test_inputs": [
89
+ "A",
90
+ "B",
91
+ "C"
92
+ ],
93
+ "token_shape": [
94
+ 3,
95
+ 2
96
+ ],
97
+ "torch_reference": {
98
+ "attention": "eager",
99
+ "dtype": "float32",
100
+ "latency_ms": 50.09009799687192
101
+ },
102
+ "variants": {
103
+ "4bit": {
104
+ "latency_ms": 9323.177823971491,
105
+ "max_abs_diff": 2.2551989555358887,
106
+ "mean_abs_diff": 1.1897996664047241
107
+ },
108
+ "8bit": {
109
+ "latency_ms": 9380.578643002082,
110
+ "max_abs_diff": 1.2797489166259766,
111
+ "mean_abs_diff": 0.542361319065094
112
+ },
113
+ "bf16": {
114
+ "latency_ms": 716.8781639775261,
115
+ "max_abs_diff": 0.04523277282714844,
116
+ "mean_abs_diff": 0.019181733950972557
117
+ }
118
+ }
119
+ },
120
+ "source_model": "feyninc/pulpie-orange-small",
121
+ "variants": [
122
+ "bf16",
123
+ "8bit",
124
+ "4bit"
125
+ ]
126
+ }