Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
 *.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 shibatch
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,378 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+language:
+  - en
+license: mit
+datasets:
+  - roneneldan/TinyStories
+tags:
+  - deepseek-v2
+  - multi-head-latent-attention
+  - mla
+  - mixture-of-experts
+  - moe
+  - tinystories
+  - tiny-model
+  - text-generation
+  - validation
+  - debug-model
+---
+
+# Tiny DeepSeek V2 3M
+
+This repository contains a tiny `DeepseekV2ForCausalLM` Mixture-of-Experts
+language model trained from scratch on TinyStories.
+
+The model has **2,928,392 parameters**. It combines DeepSeek V2-style
+Multi-head Latent Attention (MLA), compressed key/value states, decoupled
+RoPE, routed experts, and a shared expert in a compact checkpoint intended for
+implementation testing and architecture experiments.
+
+This is a synthetic tiny checkpoint. It is not an official DeepSeek model,
+does not contain weights from an original DeepSeek checkpoint, and should not
+be expected to match the quality or capabilities of production DeepSeek
+models.
+
+## Repository contents
+
+- `hf/`: the final Hugging Face checkpoint and tokenizer
+- `example_generate.py`: a minimal generation example
+- `eval_text_generation.json`: generations from the final training evaluation
+- `artifact_metadata.json`: training arguments, metrics, router usage, and the
+  expanded configuration
+- `deepseek_v2_config_dump.json`: a standalone configuration dump
+
+Optimizer checkpoints and the full training history are intentionally omitted
+from this distribution package.
+
+## Architecture identity
+
+This checkpoint uses:
+
+```text
+DeepseekV2Config
+DeepseekV2ForCausalLM
+model_type: deepseek_v2
+```
+
+It is specifically a DeepSeek V2 architecture, not DeepSeek V3 and not a
+generic dense decoder renamed as DeepSeek. The checkpoint exercises the
+DeepSeek V2 MLA and MoE implementations provided by Hugging Face Transformers.
+
+## Model architecture
+
+```yaml
+architecture: DeepseekV2ForCausalLM
+model_type: deepseek_v2
+parameter_count: 2,928,392
+
+model_vocab_size: 1,024
+tokenizer_size: 1,003
+hidden_size: 216
+intermediate_size: 432
+num_hidden_layers: 5
+
+num_attention_heads: 8
+num_key_value_heads: 8
+qk_nope_head_dim: 16
+qk_rope_head_dim: 16
+v_head_dim: 32
+q_lora_rank: null
+kv_lora_rank: 64
+
+first_k_dense_replace: 1
+n_routed_experts: 4
+n_shared_experts: 1
+num_experts_per_tok: 1
+moe_intermediate_size: 128
+topk_method: greedy
+norm_topk_prob: false
+routed_scaling_factor: 4.0
+aux_loss_alpha: 0.01
+seq_aux: true
+
+tie_word_embeddings: true
+rms_norm_eps: 1.0e-6
+max_position_embeddings: 2,048
+rope_theta: 10,000
+```
+
+## Multi-head Latent Attention
+
+Each attention head separates its query/key dimensions into:
+
+```text
+16 non-positional dimensions + 16 rotary dimensions
+```
+
+Values use 32 dimensions per head. The key/value path is compressed through a
+64-dimensional latent projection (`kv_lora_rank: 64`) before being expanded
+for attention. Query LoRA is disabled in this tiny configuration, while the
+compressed KV path and decoupled rotary/non-rotary query-key components remain
+active.
+
+This keeps the checkpoint small while exercising the defining DeepSeek V2 MLA
+code paths.
+
+## Dense and MoE layers
+
+The first decoder layer uses a dense MLP. The remaining four layers use
+DeepSeek V2 MoE blocks:
+
+```text
+layer 0: dense MLP
+layer 1: 4 routed experts, top-1 + 1 shared expert
+layer 2: 4 routed experts, top-1 + 1 shared expert
+layer 3: 4 routed experts, top-1 + 1 shared expert
+layer 4: 4 routed experts, top-1 + 1 shared expert
+```
+
+Every token is sent to one routed expert, while the shared expert is evaluated
+for all tokens. Sequence-level router auxiliary loss was enabled during
+training.
+
+All routed experts received traffic. Final aggregate routing fractions were
+close to 25% for every expert:
+
+| MoE layer | Expert 0 | Expert 1 | Expert 2 | Expert 3 |
+| ---: | ---: | ---: | ---: | ---: |
+| 1 | 0.2502 | 0.2487 | 0.2522 | 0.2488 |
+| 2 | 0.2538 | 0.2481 | 0.2487 | 0.2495 |
+| 3 | 0.2512 | 0.2454 | 0.2519 | 0.2514 |
+| 4 | 0.2465 | 0.2535 | 0.2542 | 0.2458 |
+
+## Training data
+
+The model was trained on the full TinyStories training corpus using an
+independent 1% validation split:
+
+```yaml
+selected_stories: 2,119,489
+training_stories: 2,098,294
+validation_stories: 21,195
+validation_fraction: 0.01
+
+training_blocks: 2,441,089
+validation_blocks: 24,608
+block_size: 256
+```
+
+Stories were joined into a continuous packed stream:
+
+```text
+BOS + story 1 + EOS + BOS + story 2 + EOS + ...
+```
+
+The stream was split into fixed 256-token blocks without padding. Only the
+final incomplete block was discarded.
+
+## Tokenizer
+
+The checkpoint uses a small custom byte-level BPE tokenizer. The base BPE
+vocabulary was trained with:
+
+```text
+BPE()
+ByteLevel(add_prefix_space=False)
+base_vocab_size: 1,000
+min_frequency: 2
+normalizer: None
+```
+
+Special tokens were then added at fixed IDs:
+
+```text
+<s>          -> 1000
+</s>         -> 1001
+<|im_start|> -> 1002
+```
+
+The tokenizer uses `<s>` as both BOS and padding, and `</s>` as EOS. The model
+configuration reserves 1,024 embedding rows while the tokenizer exposes
+1,003 tokens.
+
+## Training setup
+
+The checkpoint was trained from scratch in float32 on an NVIDIA GeForce GTX
+1650:
+
+```yaml
+dtype: float32
+batch_size: 16
+block_size: 256
+training_steps: 152,568
+epochs: 1.0
+tokens_processed: 624,918,528
+
+optimizer: AdamW
+learning_rate: 3.0e-4
+warmup_steps: 2,000
+scheduler: warmup + cosine decay
+minimum_learning_rate: 3.0e-5
+weight_decay: 0.0
+grad_clip: 1.0
+```
+
+## Evaluation
+
+The final checkpoint produced:
+
+```yaml
+final_train_loss: 1.4096
+validation_loss: 1.4226
+validation_perplexity: 4.1478
+```
+
+Validation loss was computed over 32 batches, or 131,072 tokens, from the
+independent packed validation split. These values are compact checkpoint
+diagnostics, not general language-model benchmark results.
+
+## Example generation
+
+One final evaluation sample for prompt `There was a little` was:
+
+```text
+There was a little girl named Lily who loved to explore. One day, she saw a
+big bush with lots of yummy peaches on it. She wanted to eat one, but her mom
+said no.
+
+Lily didn't listen and kept trying to eat her peach.
+```
+
+Sampling is stochastic. The model usually produces recognizable
+TinyStories-style English, but semantic contradictions, unfinished sentences,
+invented words, and repetition remain possible at this size.
+
+## Usage
+
+Install the requirements:
+
+```bash
+pip install -r requirements.txt
+```
+
+Run the included local example from the repository root:
+
+```bash
+python example_generate.py
+```
+
+To load the package from Hugging Face Hub, resolve the `hf` directory to a
+local path first. This avoids a Transformers 5.14.1 local-subfolder issue in
+which generation configuration lookup may incorrectly fall back to the
+repository root:
+
+```python
+from pathlib import Path
+
+import torch
+from huggingface_hub import snapshot_download
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo = "shibatch/tinydeepseekv2-3m"
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model_dir = Path(snapshot_download(
+    repo_id=repo,
+    allow_patterns=["hf/*"],
+)) / "hf"
+
+tokenizer = AutoTokenizer.from_pretrained(model_dir)
+model = AutoModelForCausalLM.from_pretrained(
+    model_dir,
+    dtype=torch.float32,
+).to(device)
+model.eval()
+
+prompt = "There was a little"
+input_ids = torch.tensor(
+    [[tokenizer.bos_token_id] + tokenizer.encode(
+        prompt,
+        add_special_tokens=False,
+    )],
+    dtype=torch.long,
+    device=device,
+)
+
+torch.manual_seed(0)
+if device.type == "cuda":
+    torch.cuda.manual_seed_all(0)
+
+with torch.no_grad():
+    output = model.generate(
+        input_ids=input_ids,
+        max_new_tokens=100,
+        do_sample=True,
+        temperature=0.8,
+        top_p=0.95,
+        top_k=40,
+        repetition_penalty=1.1,
+        pad_token_id=tokenizer.pad_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+
+print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))
+```
+
+## Loading requirements
+
+The checkpoint requires a Transformers release containing
+`DeepseekV2ForCausalLM`. It was trained and tested with:
+
+```text
+transformers 5.14.1
+torch 2.14.0.dev20260720+cu126
+```
+
+## Intended uses
+
+This model is intended for:
+
+- testing `DeepseekV2Config` and `DeepseekV2ForCausalLM`
+- testing Multi-head Latent Attention and compressed KV states
+- exercising decoupled rotary and non-rotary query/key dimensions
+- testing dense-to-MoE layer transitions
+- testing top-1 routed experts and shared experts
+- checking sequence-level router load-balancing loss
+- exercising custom tokenizer loading
+- testing `generate()`, `save_pretrained()`, and `from_pretrained()`
+- compact inference-engine and architecture experiments
+
+It is not intended for:
+
+- instruction following or chat
+- factual question answering
+- high-quality long-form generation
+- production deployment
+- safety-critical use
+- benchmark comparison with production DeepSeek models
+
+## Limitations
+
+Known limitations include:
+
+- only 2.93 million parameters
+- small 1,003-token tokenizer
+- English TinyStories-only pretraining
+- weak factual knowledge and reasoning
+- no instruction tuning or chat template
+- occasional grammatical and semantic errors
+- invented words and truncated sentences
+- repetition and template-like stories
+- no quality-equivalence claim with official DeepSeek models
+- no current llama.cpp or GGUF inference support assumed for this exact
+  DeepSeek V2 MLA/MoE configuration
+
+## Notes on GGUF
+
+The checkpoint is distributed as a normal float32 Hugging Face Safetensors
+model. A useful GGUF build requires converter and runtime support for this
+DeepSeek V2 MLA and MoE graph, including compressed KV projections, decoupled
+RoPE, routed experts, and the shared expert. Merely placing tensors in a GGUF
+container is not sufficient for compatible inference.
+
+## Citation
+
+This is a synthetic tiny DeepSeek V2-compatible MoE checkpoint trained from
+scratch on TinyStories. It is intended for implementation validation,
+debugging, education, and small-scale architecture experiments.

artifact_metadata.json

@@ -0,0 +1,182 @@
+{
+  "model_type": "deepseek_v2_moe",
+  "hf_model_type": "deepseek_v2",
+  "parameter_count": 2928392,
+  "tokenizer_size": 1003,
+  "final_eval_loss": 1.4225675538182259,
+  "final_eval_ppl": 4.1477563679496425,
+  "final_train_lm_loss": 1.409641880750656,
+  "router_usage": {
+    "model.layers.1.mlp.gate": [
+      0.2502,
+      0.2487,
+      0.2522,
+      0.2488
+    ],
+    "model.layers.2.mlp.gate": [
+      0.2538,
+      0.2481,
+      0.2487,
+      0.2495
+    ],
+    "model.layers.3.mlp.gate": [
+      0.2512,
+      0.2454,
+      0.2519,
+      0.2514
+    ],
+    "model.layers.4.mlp.gate": [
+      0.2465,
+      0.2535,
+      0.2542,
+      0.2458
+    ]
+  },
+  "args": {
+    "train_files": [
+      "data/train-00000-of-00004-2d5a1467fff1081b.parquet",
+      "data/train-00001-of-00004-5852b56a2bd28fd9.parquet",
+      "data/train-00002-of-00004-a26307300439e943.parquet",
+      "data/train-00003-of-00004-d243063613e5a057.parquet"
+    ],
+    "output_dir": "runs/deepseek_v2_3m_fix2_100p_1epoch",
+    "max_rows": 0,
+    "data_fraction": 1.0,
+    "vocab_size": 1024,
+    "base_vocab_size": 1000,
+    "min_frequency": 2,
+    "legacy_tokenizer": true,
+    "legacy_special_token_ids": true,
+    "deepseek_arch": "v2",
+    "hidden_size": 216,
+    "intermediate_size": 432,
+    "num_hidden_layers": 5,
+    "num_attention_heads": 8,
+    "num_key_value_heads": 8,
+    "qk_nope_head_dim": 16,
+    "qk_rope_head_dim": 16,
+    "v_head_dim": 32,
+    "q_lora_rank": -1,
+    "kv_lora_rank": 64,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "rms_norm_eps": 1e-06,
+    "initializer_range": 0.02,
+    "rope_theta": 10000,
+    "first_k_dense_replace": 1,
+    "n_routed_experts": 4,
+    "n_shared_experts": 1,
+    "num_experts_per_tok": 1,
+    "n_group": 0,
+    "topk_group": 0,
+    "topk_method": "greedy",
+    "norm_topk_prob": false,
+    "routed_scaling_factor": 4.0,
+    "moe_intermediate_size": 128,
+    "router_aux_loss_alpha": 0.01,
+    "official_router_init": true,
+    "max_position_embeddings": 2048,
+    "tie_word_embeddings": true,
+    "use_cache": false,
+    "mlp_bias": false,
+    "block_size": 256,
+    "batch_size": 16,
+    "max_steps": 152568,
+    "num_epochs": 1.0,
+    "learning_rate": 0.0003,
+    "weight_decay": 0.0,
+    "grad_clip": 1.0,
+    "warmup_steps": 2000,
+    "min_lr_ratio": 0.1,
+    "validation_fraction": 0.01,
+    "log_steps": 500,
+    "eval_steps": 10000,
+    "eval_batches": 32,
+    "save_steps": 10000,
+    "resume_from_checkpoint": "",
+    "seed": 1234,
+    "dtype": "float32",
+    "device": "cuda",
+    "num_workers": 0,
+    "generate_prompts": [
+      "Once upon",
+      "There was a little",
+      "One day"
+    ],
+    "generate_new_tokens": 100,
+    "generation_temperature": 0.8,
+    "generation_top_p": 0.95,
+    "generation_top_k": 40,
+    "generation_repetition_penalty": 1.1,
+    "do_sample": true
+  },
+  "config": {
+    "transformers_version": "5.14.1",
+    "architectures": [
+      "DeepseekV2ForCausalLM"
+    ],
+    "output_hidden_states": false,
+    "return_dict": true,
+    "dtype": "float32",
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "problem_type": null,
+    "vocab_size": 1024,
+    "hidden_size": 216,
+    "intermediate_size": 432,
+    "num_hidden_layers": 5,
+    "num_attention_heads": 8,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "max_position_embeddings": 2048,
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "use_cache": false,
+    "pad_token_id": 1000,
+    "bos_token_id": 1000,
+    "eos_token_id": 1001,
+    "pretraining_tp": 1,
+    "tie_word_embeddings": true,
+    "rope_parameters": {
+      "rope_type": "default",
+      "rope_theta": 10000
+    },
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "mlp_bias": false,
+    "head_dim": 16,
+    "first_k_dense_replace": 1,
+    "kv_lora_rank": 64,
+    "q_lora_rank": null,
+    "n_group": null,
+    "n_routed_experts": 4,
+    "n_shared_experts": 1,
+    "qk_nope_head_dim": 16,
+    "qk_rope_head_dim": 16,
+    "routed_scaling_factor": 4.0,
+    "topk_group": null,
+    "topk_method": "greedy",
+    "norm_topk_prob": false,
+    "v_head_dim": 32,
+    "num_experts_per_tok": 1,
+    "moe_intermediate_size": 128,
+    "_name_or_path": "",
+    "aux_loss_alpha": 0.01,
+    "seq_aux": true,
+    "model_type": "deepseek_v2",
+    "output_attentions": false
+  },
+  "generations": {
+    "Once upon": "Once upon a time, there was a little boy named Timmy. He loved to play in the sand and splash in the water. One day, he was playing with his toy car when it slipped on some rocks. His mom came and said, \"Oh no, I'm sorry! Let's bury something that is not ours so we can find out.\"\n\nTimmy didn't understand what \"oray\" meant, but",
+    "There was a little": "There was a little girl named Lily who loved to explore. One day, she saw a big bush with lots of yummy peaches on it. She wanted to eat one, but her mom said no.\n\nLily didn't listen and kept trying to eat her peach. She tried and tried but the bush wouldn't eat. Finally, she ate all the peaches and started to feel sick. Her mom told her not to eat",
+    "One day": "One day, the boy saw a palace in the park. He thought it was the most special palace he had ever seen! He wanted to play with it, so he called out to his friend, Alice.\n\nAlice asked the palace: \"Can I go in?\"\n\nHis friend replied: \"Yes, but you must be very kind and gentle. What do you think?\"\n\n"
+  }
+}

deepseek_v2_config_dump.json

@@ -0,0 +1,62 @@
+{
+  "transformers_version": "5.14.1",
+  "architectures": null,
+  "output_hidden_states": false,
+  "return_dict": true,
+  "dtype": null,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "problem_type": null,
+  "vocab_size": 1024,
+  "hidden_size": 216,
+  "intermediate_size": 432,
+  "num_hidden_layers": 5,
+  "num_attention_heads": 8,
+  "num_key_value_heads": 8,
+  "hidden_act": "silu",
+  "max_position_embeddings": 2048,
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-06,
+  "use_cache": false,
+  "pad_token_id": 1000,
+  "bos_token_id": 1000,
+  "eos_token_id": 1001,
+  "pretraining_tp": 1,
+  "tie_word_embeddings": true,
+  "rope_parameters": {
+    "rope_type": "default",
+    "rope_theta": 10000
+  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "mlp_bias": false,
+  "head_dim": 16,
+  "first_k_dense_replace": 1,
+  "kv_lora_rank": 64,
+  "q_lora_rank": null,
+  "n_group": null,
+  "n_routed_experts": 4,
+  "n_shared_experts": 1,
+  "qk_nope_head_dim": 16,
+  "qk_rope_head_dim": 16,
+  "routed_scaling_factor": 4.0,
+  "topk_group": null,
+  "topk_method": "greedy",
+  "norm_topk_prob": false,
+  "v_head_dim": 32,
+  "num_experts_per_tok": 1,
+  "moe_intermediate_size": 128,
+  "_name_or_path": "",
+  "aux_loss_alpha": 0.01,
+  "seq_aux": true,
+  "model_type": "deepseek_v2",
+  "output_attentions": false
+}

eval_text_generation.json

@@ -0,0 +1,5 @@
+{
+  "Once upon": "Once upon a time, there was a little boy named Timmy. He loved to play in the sand and splash in the water. One day, he was playing with his toy car when it slipped on some rocks. His mom came and said, \"Oh no, I'm sorry! Let's bury something that is not ours so we can find out.\"\n\nTimmy didn't understand what \"oray\" meant, but",
+  "There was a little": "There was a little girl named Lily who loved to explore. One day, she saw a big bush with lots of yummy peaches on it. She wanted to eat one, but her mom said no.\n\nLily didn't listen and kept trying to eat her peach. She tried and tried but the bush wouldn't eat. Finally, she ate all the peaches and started to feel sick. Her mom told her not to eat",
+  "One day": "One day, the boy saw a palace in the park. He thought it was the most special palace he had ever seen! He wanted to play with it, so he called out to his friend, Alice.\n\nAlice asked the palace: \"Can I go in?\"\n\nHis friend replied: \"Yes, but you must be very kind and gentle. What do you think?\"\n\n"
+}

example_generate.py

@@ -0,0 +1,53 @@
+from pathlib import Path
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+
+MODEL_PATH = "."
+MODEL_SUBFOLDER = "hf"
+PROMPT = "There was a little"
+SEED = 0
+
+
+def main() -> None:
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model_dir = Path(MODEL_PATH) / MODEL_SUBFOLDER
+    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+    model = AutoModelForCausalLM.from_pretrained(
+        model_dir,
+        dtype=torch.float32,
+    ).to(device)
+    model.eval()
+
+    input_ids = torch.tensor(
+        [
+            [tokenizer.bos_token_id]
+            + tokenizer.encode(PROMPT, add_special_tokens=False)
+        ],
+        dtype=torch.long,
+        device=device,
+    )
+
+    torch.manual_seed(SEED)
+    if device.type == "cuda":
+        torch.cuda.manual_seed_all(SEED)
+
+    with torch.no_grad():
+        output = model.generate(
+            input_ids=input_ids,
+            max_new_tokens=100,
+            do_sample=True,
+            temperature=0.8,
+            top_p=0.95,
+            top_k=40,
+            repetition_penalty=1.1,
+            pad_token_id=tokenizer.pad_token_id,
+            eos_token_id=tokenizer.eos_token_id,
+        )
+
+    print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))
+
+
+if __name__ == "__main__":
+    main()

hf/config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "DeepseekV2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "aux_loss_alpha": 0.01,
+  "bos_token_id": 1000,
+  "dtype": "float32",
+  "eos_token_id": 1001,
+  "first_k_dense_replace": 1,
+  "head_dim": 16,
+  "hidden_act": "silu",
+  "hidden_size": 216,
+  "initializer_range": 0.02,
+  "intermediate_size": 432,
+  "kv_lora_rank": 64,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "deepseek_v2",
+  "moe_intermediate_size": 128,
+  "n_group": null,
+  "n_routed_experts": 4,
+  "n_shared_experts": 1,
+  "norm_topk_prob": false,
+  "num_attention_heads": 8,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 5,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1000,
+  "pretraining_tp": 1,
+  "q_lora_rank": null,
+  "qk_nope_head_dim": 16,
+  "qk_rope_head_dim": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 4.0,
+  "seq_aux": true,
+  "tie_word_embeddings": true,
+  "topk_group": null,
+  "topk_method": "greedy",
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "v_head_dim": 32,
+  "vocab_size": 1024
+}

hf/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1000,
+  "eos_token_id": 1001,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1000,
+  "transformers_version": "5.14.1",
+  "use_cache": false
+}

hf/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0dc89f00aeb1e7faabe33eade2d1df619ae2b3c2d903f86443e7409b1fb3e3c
+size 11725296

hf/tokenizer.json

@@ -0,0 +1,4063 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 1000,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1001,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1002,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": false,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "!": 0,
+      "\"": 1,
+      "#": 2,
+      "$": 3,
+      "%": 4,
+      "&": 5,
+      "'": 6,
+      "(": 7,
+      ")": 8,
+      "*": 9,
+      "+": 10,
+      ",": 11,
+      "-": 12,
+      ".": 13,
+      "/": 14,
+      "0": 15,
+      "1": 16,
+      "2": 17,
+      "3": 18,
+      "4": 19,
+      "5": 20,
+      "6": 21,
+      "7": 22,
+      "8": 23,
+      "9": 24,
+      ":": 25,
+      ";": 26,
+      "<": 27,
+      "=": 28,
+      ">": 29,
+      "?": 30,
+      "@": 31,
+      "A": 32,
+      "B": 33,
+      "C": 34,
+      "D": 35,
+      "E": 36,
+      "F": 37,
+      "G": 38,
+      "H": 39,
+      "I": 40,
+      "J": 41,
+      "K": 42,
+      "L": 43,
+      "M": 44,
+      "N": 45,
+      "O": 46,
+      "P": 47,
+      "Q": 48,
+      "R": 49,
+      "S": 50,
+      "T": 51,
+      "U": 52,
+      "V": 53,
+      "W": 54,
+      "X": 55,
+      "Y": 56,
+      "Z": 57,
+      "[": 58,
+      "\\": 59,
+      "]": 60,
+      "^": 61,
+      "_": 62,
+      "`": 63,
+      "a": 64,
+      "b": 65,
+      "c": 66,
+      "d": 67,
+      "e": 68,
+      "f": 69,
+      "g": 70,
+      "h": 71,
+      "i": 72,
+      "j": 73,
+      "k": 74,
+      "l": 75,
+      "m": 76,
+      "n": 77,
+      "o": 78,
+      "p": 79,
+      "q": 80,
+      "r": 81,
+      "s": 82,
+      "t": 83,
+      "u": 84,
+      "v": 85,
+      "w": 86,
+      "x": 87,
+      "y": 88,
+      "z": 89,
+      "{": 90,
+      "|": 91,
+      "}": 92,
+      "~": 93,
+      "¡": 94,
+      "¢": 95,
+      "£": 96,
+      "¤": 97,
+      "¥": 98,
+      "¦": 99,
+      "§": 100,
+      "¨": 101,
+      "©": 102,
+      "ª": 103,
+      "«": 104,
+      "¬": 105,
+      "®": 106,
+      "¯": 107,
+      "°": 108,
+      "±": 109,
+      "²": 110,
+      "³": 111,
+      "´": 112,
+      "µ": 113,
+      "¶": 114,
+      "·": 115,
+      "¸": 116,
+      "¹": 117,
+      "º": 118,
+      "»": 119,
+      "¼": 120,
+      "½": 121,
+      "¾": 122,
+      "¿": 123,
+      "À": 124,
+      "Á": 125,
+      "Â": 126,
+      "Ã": 127,
+      "Ä": 128,
+      "Å": 129,
+      "Æ": 130,
+      "Ç": 131,
+      "È": 132,
+      "É": 133,
+      "Ê": 134,
+      "Ë": 135,
+      "Ì": 136,
+      "Í": 137,
+      "Î": 138,
+      "Ï": 139,
+      "Ð": 140,
+      "Ñ": 141,
+      "Ò": 142,
+      "Ó": 143,
+      "Ô": 144,
+      "Õ": 145,
+      "Ö": 146,
+      "×": 147,
+      "Ø": 148,
+      "Ù": 149,
+      "Ú": 150,
+      "Û": 151,
+      "Ü": 152,
+      "Ý": 153,
+      "Þ": 154,
+      "ß": 155,
+      "à": 156,
+      "á": 157,
+      "â": 158,
+      "ã": 159,
+      "ä": 160,
+      "å": 161,
+      "æ": 162,
+      "ç": 163,
+      "è": 164,
+      "é": 165,
+      "ê": 166,
+      "ë": 167,
+      "ì": 168,
+      "í": 169,
+      "î": 170,
+      "ï": 171,
+      "ð": 172,
+      "ñ": 173,
+      "ò": 174,
+      "ó": 175,
+      "ô": 176,
+      "õ": 177,
+      "ö": 178,
+      "÷": 179,
+      "ø": 180,
+      "ù": 181,
+      "ú": 182,
+      "û": 183,
+      "ü": 184,
+      "ý": 185,
+      "þ": 186,
+      "ÿ": 187,
+      "Ā": 188,
+      "ā": 189,
+      "Ă": 190,
+      "ă": 191,
+      "Ą": 192,
+      "ą": 193,
+      "Ć": 194,
+      "ć": 195,
+      "Ĉ": 196,
+      "ĉ": 197,
+      "Ċ": 198,
+      "ċ": 199,
+      "Č": 200,
+      "č": 201,
+      "Ď": 202,
+      "ď": 203,
+      "Đ": 204,
+      "đ": 205,
+      "Ē": 206,
+      "ē": 207,
+      "Ĕ": 208,
+      "ĕ": 209,
+      "Ė": 210,
+      "ė": 211,
+      "Ę": 212,
+      "ę": 213,
+      "Ě": 214,
+      "ě": 215,
+      "Ĝ": 216,
+      "ĝ": 217,
+      "Ğ": 218,
+      "ğ": 219,
+      "Ġ": 220,
+      "ġ": 221,
+      "Ģ": 222,
+      "ģ": 223,
+      "Ĥ": 224,
+      "ĥ": 225,
+      "Ħ": 226,
+      "ħ": 227,
+      "Ĩ": 228,
+      "ĩ": 229,
+      "Ī": 230,
+      "ī": 231,
+      "Ĭ": 232,
+      "ĭ": 233,
+      "Į": 234,
+      "į": 235,
+      "İ": 236,
+      "ı": 237,
+      "IJ": 238,
+      "ij": 239,
+      "Ĵ": 240,
+      "ĵ": 241,
+      "Ķ": 242,
+      "ķ": 243,
+      "ĸ": 244,
+      "Ĺ": 245,
+      "ĺ": 246,
+      "Ļ": 247,
+      "ļ": 248,
+      "Ľ": 249,
+      "ľ": 250,
+      "Ŀ": 251,
+      "ŀ": 252,
+      "Ł": 253,
+      "ł": 254,
+      "Ń": 255,
+      "he": 256,
+      "Ġt": 257,
+      "Ġa": 258,
+      "Ġs": 259,
+      "Ġw": 260,
+      "nd": 261,
+      "Ġthe": 262,
+      "ed": 263,
+      "Ġand": 264,
+      "Ġto": 265,
+      "Ġb": 266,
+      "in": 267,
+      "Ġh": 268,
+      "Ġwa": 269,
+      "re": 270,
+      "ou": 271,
+      "Ġf": 272,
+      "it": 273,
+      "Ġl": 274,
+      "Ġc": 275,
+      "Ġd": 276,
+      "er": 277,
+      "Ġhe": 278,
+      "Ġm": 279,
+      "Ġp": 280,
+      "Ġwas": 281,
+      "om": 282,
+      "ĠT": 283,
+      "Ġo": 284,
+      "ay": 285,
+      "ar": 286,
+      "is": 287,
+      "ing": 288,
+      "il": 289,
+      "Ġg": 290,
+      "id": 291,
+      "at": 292,
+      "en": 293,
+      "Ġn": 294,
+      "Ġsa": 295,
+      "Ġha": 296,
+      "ĠS": 297,
+      "ĠThe": 298,
+      "an": 299,
+      "im": 300,
+      "or": 301,
+      "on": 302,
+      "Ġit": 303,
+      "Ġth": 304,
+      "ll": 305,
+      "le": 306,
+      "ĠH": 307,
+      "Ġher": 308,
+      "ot": 309,
+      "et": 310,
+      "ir": 311,
+      "ĠShe": 312,
+      "es": 313,
+      "ĠHe": 314,
+      "Ġin": 315,
+      "ver": 316,
+      "ut": 317,
+      "ow": 318,
+      "ĠThey": 319,
+      "ck": 320,
+      "Ġe": 321,
+      "Ġu": 322,
+      "ld": 323,
+      "Ġy": 324,
+      "oo": 325,
+      "Ġsaid": 326,
+      "ig": 327,
+      "ily": 328,
+      "Ġ\"": 329,
+      "Ġr": 330,
+      "Ġbe": 331,
+      "am": 332,
+      "Ġst": 333,
+      "ĠI": 334,
+      "ce": 335,
+      "ke": 336,
+      "Ġshe": 337,
+      "ve": 338,
+      "pp": 339,
+      "ith": 340,
+      "Ġwith": 341,
+      "Lily": 342,
+      "On": 343,
+      "Ġon": 344,
+      "Ġyou": 345,
+      "Ġof": 346,
+      "ked": 347,
+      "ri": 348,
+      "Ġso": 349,
+      "nt": 350,
+      "Ġhis": 351,
+      "Ġpl": 352,
+      "ad": 353,
+      "very": 354,
+      "Ġday": 355,
+      "Ġthat": 356,
+      "Ġup": 357,
+      "Ġplay": 358,
+      "Ġhad": 359,
+      "st": 360,
+      "Ġthey": 361,
+      "Ġwe": 362,
+      "ĠLily": 363,
+      "Ġmom": 364,
+      "Ġfor": 365,
+      "ĠB": 366,
+      "el": 367,
+      "un": 368,
+      "ould": 369,
+      "'s": 370,
+      "my": 371,
+      "The": 372,
+      "Ġli": 373,
+      "ch": 374,
+      "ent": 375,
+      "Ġhapp": 376,
+      "Ġwant": 377,
+      "itt": 378,
+      "Ġsh": 379,
+      "out": 380,
+      "her": 381,
+      "Ġdo": 382,
+      "ly": 383,
+      "Ġnot": 384,
+      "ome": 385,
+      "se": 386,
+      "Ġvery": 387,
+      "ound": 388,
+      "end": 389,
+      "all": 390,
+      "Ġwh": 391,
+      "ime": 392,
+      "ittle": 393,
+      "Ġk": 394,
+      "Ġtime": 395,
+      "Ġlittle": 396,
+      "al": 397,
+      "ĠĊ": 398,
+      "Ġthere": 399,
+      "Ġne": 400,
+      "ht": 401,
+      "ĠM": 402,
+      "Ġre": 403,
+      "Ġhappy": 404,
+      "Ġsm": 405,
+      "Ġbig": 406,
+      "Ġis": 407,
+      "ĠIt": 408,
+      "Ġbut": 409,
+      "ack": 410,
+      "Ġan": 411,
+      "Ġsaw": 412,
+      "riend": 413,
+      ".\"": 414,
+      "Ġfriend": 415,
+      "ry": 416,
+      "Ġas": 417,
+      "ra": 418,
+      "One": 419,
+      "ide": 420,
+      "ake": 421,
+      "'t": 422,
+      "!\"": 423,
+      "ug": 424,
+      "Ġloo": 425,
+      "ved": 426,
+      "ter": 427,
+      "Ġwere": 428,
+      "ore": 429,
+      "Once": 430,
+      "Ġlo": 431,
+      "ec": 432,
+      "Ġhim": 433,
+      "Ġtoo": 434,
+      "Ġgo": 435,
+      "Ġbo": 436,
+      "Ġse": 437,
+      "irl": 438,
+      "Ġare": 439,
+      "Ġj": 440,
+      "ĠTim": 441,
+      "ard": 442,
+      "Ġwanted": 443,
+      "ill": 444,
+      "Ġgirl": 445,
+      "Ġupon": 446,
+      "Ġthem": 447,
+      "Ġout": 448,
+      "Ġat": 449,
+      "ur": 450,
+      "ind": 451,
+      "Ġtheir": 452,
+      "fu": 453,
+      "Ġsp": 454,
+      "way": 455,
+      "ĠA": 456,
+      "Ġsmil": 457,
+      "Ġdid": 458,
+      "Ġcould": 459,
+      "hen": 460,
+      "Ġhave": 461,
+      "ain": 462,
+      "art": 463,
+      "Ġex": 464,
+      "hed": 465,
+      "rom": 466,
+      "Ġwent": 467,
+      "Ġar": 468,
+      "ic": 469,
+      "Ġcan": 470,
+      "ĠJ": 471,
+      "lp": 472,
+      "ful": 473,
+      "ĠBen": 474,
+      "ood": 475,
+      "?\"": 476,
+      "hing": 477,
+      "Ġfriends": 478,
+      "Ġnam": 479,
+      "ight": 480,
+      "Ġall": 481,
+      "Ġhelp": 482,
+      "Ġkn": 483,
+      "um": 484,
+      "ark": 485,
+      "one": 486,
+      "Ġback": 487,
+      "Ġsay": 488,
+      "You": 489,
+      "Ġfun": 490,
+      "Ġcl": 491,
+      "ĠTom": 492,
+      "are": 493,
+      "Ġno": 494,
+      "Ġle": 495,
+      "op": 496,
+      "Ġsmiled": 497,
+      "Ġsc": 498,
+      "Ġnamed": 499,
+      "Ġal": 500,
+      "oug": 501,
+      "Ġloved": 502,
+      "side": 503,
+      "elt": 504,
+      "ĠOne": 505,
+      "Ġman": 506,
+      "Ġasked": 507,
+      "ick": 508,
+      "Ġtoy": 509,
+      "Ġlike": 510,
+      "Ġfe": 511,
+      "Ġfelt": 512,
+      "Ġlooked": 513,
+      "Ġsome": 514,
+      "Ġsee": 515,
+      "Ġaround": 516,
+      "Ġme": 517,
+      "ame": 518,
+      "omet": 519,
+      "ĠW": 520,
+      "Ġro": 521,
+      "Ġbr": 522,
+      "ure": 523,
+      "ĠTimmy": 524,
+      "Ġbir": 525,
+      "get": 526,
+      "ice": 527,
+      "Ġboy": 528,
+      "Ġwould": 529,
+      "Ġstart": 530,
+      "ong": 531,
+      "â": 532,
+      "âĤ": 533,
+      "âĤ¬": 534,
+      "ss": 535,
+      "Ġbird": 536,
+      "Ġsomet": 537,
+      "Ġfa": 538,
+      "dd": 539,
+      "ings": 540,
+      "Ġag": 541,
+      "Ġwor": 542,
+      "Ġwhat": 543,
+      "ade": 544,
+      "Ġmake": 545,
+      "king": 546,
+      ",\"": 547,
+      "ie": 548,
+      "ĠBut": 549,
+      "own": 550,
+      "Ġtre": 551,
+      "Ġran": 552,
+      "gether": 553,
+      "ĠYou": 554,
+      "Ġaway": 555,
+      "ag": 556,
+      "ared": 557,
+      "Ġsays": 558,
+      "Ġstarted": 559,
+      "oud": 560,
+      "if": 561,
+      "Ġmade": 562,
+      "Ġcar": 563,
+      "Ġsomething": 564,
+      "Ġtogether": 565,
+      "ited": 566,
+      "ther": 567,
+      "Ġpark": 568,
+      "Ġco": 569,
+      "Ġsad": 570,
+      "Ġother": 571,
+      "Ġnew": 572,
+      "Ġexc": 573,
+      "Ġput": 574,
+      "Ġfrom": 575,
+      "Ġpr": 576,
+      "ell": 577,
+      "ĠL": 578,
+      "Ġla": 579,
+      "Ġhug": 580,
+      "ble": 581,
+      "ook": 582,
+      "Ġmu": 583,
+      "ach": 584,
+      "Ġagain": 585,
+      "Ġhome": 586,
+      "Ġwhen": 587,
+      "Ġgood": 588,
+      "ep": 589,
+      "hat": 590,
+      "Ġwho": 591,
+      "est": 592,
+      "ried": 593,
+      "Ġfound": 594,
+      "Ġfl": 595,
+      "Ġthen": 596,
+      "Ġch": 597,
+      "Ġdec": 598,
+      "pped": 599,
+      "Ġwal": 600,
+      "as": 601,
+      "Ġget": 602,
+      "qu": 603,
+      "Ġplaying": 604,
+      "ought": 605,
+      "pl": 606,
+      "ĠE": 607,
+      "ally": 608,
+      "Ġsw": 609,
+      "ous": 610,
+      "nn": 611,
+      "Ġthings": 612,
+      "Ġexcited": 613,
+      "Ġliked": 614,
+      "Ġgot": 615,
+      "uck": 616,
+      "ro": 617,
+      "ided": 618,
+      "Ġdecided": 619,
+      "Ġbl": 620,
+      "ave": 621,
+      "Ġcame": 622,
+      "Ġevery": 623,
+      "ara": 624,
+      "ĠMom": 625,
+      "Ġyour": 626,
+      "ĠD": 627,
+      "ax": 628,
+      "Ġv": 629,
+      "Ġscared": 630,
+      "ust": 631,
+      "Ġone": 632,
+      "Ġdog": 633,
+      "Ġdown": 634,
+      "ouse": 635,
+      "ny": 636,
+      "Ġfind": 637,
+      "Ġcare": 638,
+      "Ġbec": 639,
+      "ist": 640,
+      "Ġthan": 641,
+      "Ġfeel": 642,
+      "ap": 643,
+      "ue": 644,
+      "udd": 645,
+      "nna": 646,
+      "Ġdad": 647,
+      "Ġab": 648,
+      "They": 649,
+      "Ġmy": 650,
+      "Ġlook": 651,
+      "Ġke": 652,
+      "our": 653,
+      "Ġwill": 654,
+      "arn": 655,
+      "Ġgr": 656,
+      "us": 657,
+      "nder": 658,
+      "Ġgra": 659,
+      "ways": 660,
+      "ess": 661,
+      "Ġdidn": 662,
+      "Ġpo": 663,
+      "fe": 664,
+      "Ġalways": 665,
+      "Ġtook": 666,
+      "Ġabout": 667,
+      "ant": 668,
+      "bb": 669,
+      "Ġmommy": 670,
+      "Ġlot": 671,
+      "Ġtoys": 672,
+      "Ġkne": 673,
+      "ers": 674,
+      "ise": 675,
+      "ite": 676,
+      "Ġoutside": 677,
+      "Ġtree": 678,
+      "Ġthought": 679,
+      "Ġball": 680,
+      "ĠF": 681,
+      "Ġmore": 682,
+      "eci": 683,
+      "ĠSam": 684,
+      "ened": 685,
+      "ched": 686,
+      "Ġta": 687,
+      "Ġold": 688,
+      "Ġho": 689,
+      "Ġlearn": 690,
+      "ret": 691,
+      "Ġint": 692,
+      "ged": 693,
+      "Ġknow": 694,
+      "Ġlaug": 695,
+      "Ġtake": 696,
+      "ecial": 697,
+      "Ġsor": 698,
+      "Ġspecial": 699,
+      "Ġcat": 700,
+      "udden": 701,
+      "Ġknew": 702,
+      "ĠMax": 703,
+      "ive": 704,
+      "ia": 705,
+      "Ġpe": 706,
+      "Ġany": 707,
+      "uddenly": 708,
+      "Ġtr": 709,
+      "fter": 710,
+      "Ġhow": 711,
+      "ma": 712,
+      "Ġshow": 713,
+      "ink": 714,
+      "Ġsorry": 715,
+      "Ġtw": 716,
+      "But": 717,
+      "Ġmuch": 718,
+      "au": 719,
+      "Ġrun": 720,
+      "ish": 721,
+      "and": 722,
+      "Ġhand": 723,
+      "Ġsl": 724,
+      "ven": 725,
+      "Ġhouse": 726,
+      "Ġor": 727,
+      "Ġop": 728,
+      "Ġsk": 729,
+      "Ġmo": 730,
+      "Ġclo": 731,
+      "Ġsun": 732,
+      "Ġinto": 733,
+      "Ġtried": 734,
+      "Ġinside": 735,
+      "ate": 736,
+      "Ġtold": 737,
+      "Ġwater": 738,
+      "Ġthis": 739,
+      "ank": 740,
+      "Ġen": 741,
+      "Ġif": 742,
+      "Ġproud": 743,
+      "ump": 744,
+      "Ġqu": 745,
+      "Ġover": 746,
+      "Tom": 747,
+      "Ġcouldn": 748,
+      "dy": 749,
+      "Ġgave": 750,
+      "Ġheard": 751,
+      "ĠSara": 752,
+      "Ġnever": 753,
+      "by": 754,
+      "Ġeach": 755,
+      "ace": 756,
+      "Ġroom": 757,
+      "ty": 758,
+      "Ġexpl": 759,
+      "ĠEvery": 760,
+      "Ġeat": 761,
+      "ĠWe": 762,
+      "other": 763,
+      "ause": 764,
+      "Ġpick": 765,
+      "ion": 766,
+      "Ġpret": 767,
+      "ĠAnna": 768,
+      "Mom": 769,
+      "Ġplayed": 770,
+      "ge": 771,
+      "etter": 772,
+      "Ġjust": 773,
+      "ak": 774,
+      "Ġhugged": 775,
+      "Ġgre": 776,
+      "here": 777,
+      "Ġoff": 778,
+      "Ġcom": 779,
+      "Ġwat": 780,
+      "oth": 781,
+      "Ġbox": 782,
+      "Ġnice": 783,
+      "'m": 784,
+      "Ġstr": 785,
+      "Ġneed": 786,
+      "Ġbecause": 787,
+      "ile": 788,
+      "Ġmany": 789,
+      "Ġfo": 790,
+      "uc": 791,
+      "Ġjo": 792,
+      "Ġbear": 793,
+      "Ġsmall": 794,
+      "iz": 795,
+      "Ġbu": 796,
+      "ving": 797,
+      "Ġlong": 798,
+      "ine": 799,
+      "gry": 800,
+      "imal": 801,
+      "ort": 802,
+      "Ġanimal": 803,
+      "Ġsn": 804,
+      "ough": 805,
+      "Ġtry": 806,
+      "Ġunt": 807,
+      "ild": 808,
+      "sel": 809,
+      "urt": 810,
+      "Ġuntil": 811,
+      "ĠJack": 812,
+      "sed": 813,
+      "Ġlearned": 814,
+      "Ġkind": 815,
+      "Ġim": 816,
+      "Ġlove": 817,
+      "Ġbetter": 818,
+      "ft": 819,
+      "Ġcall": 820,
+      "Ġflow": 821,
+      "Ġdon": 822,
+      "He": 823,
+      "ĠJo": 824,
+      "Ġend": 825,
+      "Ġad": 826,
+      "ull": 827,
+      "Ġbest": 828,
+      "vent": 829,
+      "Yes": 830,
+      "ars": 831,
+      "urp": 832,
+      "ady": 833,
+      "em": 834,
+      "ream": 835,
+      "aut": 836,
+      "urn": 837,
+      "ĠMia": 838,
+      "Ġcle": 839,
+      "ĠAnd": 840,
+      "ves": 841,
+      "Åĵ": 842,
+      "ĠC": 843,
+      "arden": 844,
+      "Ġgarden": 845,
+      "Ġfast": 846,
+      "ber": 847,
+      "Ġcareful": 848,
+      "Ġbeaut": 849,
+      "lly": 850,
+      "Th": 851,
+      "Ġeven": 852,
+      "pt": 853,
+      "Ġbra": 854,
+      "ies": 855,
+      "Ġthanked": 856,
+      "Ġfi": 857,
+      "ĠSo": 858,
+      "Ġche": 859,
+      "Ġlaughed": 860,
+      "Ġsky": 861,
+      "Ġby": 862,
+      "It": 863,
+      "ĠHer": 864,
+      "Ġjump": 865,
+      "Ġgl": 866,
+      "ase": 867,
+      "Ġte": 868,
+      "Ġloud": 869,
+      "self": 870,
+      "iny": 871,
+      "Ġway": 872,
+      "wn": 873,
+      "Ġbeauti": 874,
+      "Ġcome": 875,
+      "lew": 876,
+      "Ġlist": 877,
+      "Ġwo": 878,
+      "Ġbeautiful": 879,
+      "Ġhard": 880,
+      "Ġlots": 881,
+      "Ġra": 882,
+      "Ġstill": 883,
+      "Ġfam": 884,
+      "Ġanimals": 885,
+      "Ġâ": 886,
+      "Ġhurt": 887,
+      "Ġunder": 888,
+      "ĠThen": 889,
+      "ect": 890,
+      "Ġstay": 891,
+      "ning": 892,
+      "Ġlet": 893,
+      "ct": 894,
+      "Ġboth": 895,
+      "Ġcu": 896,
+      "ĠHis": 897,
+      "hes": 898,
+      "be": 899,
+      "Ġsafe": 900,
+      "ĠFrom": 901,
+      "ool": 902,
+      "ree": 903,
+      "Ġcol": 904,
+      "Ġtwo": 905,
+      "Ġbad": 906,
+      "Ġbook": 907,
+      "Ġimp": 908,
+      "Ġrem": 909,
+      "ople": 910,
+      "ane": 911,
+      "Ġlived": 912,
+      "kay": 913,
+      "ock": 914,
+      "ucy": 915,
+      "Ġwalked": 916,
+      "Tim": 917,
+      "ast": 918,
+      "urpr": 919,
+      "Ġbrave": 920,
+      "Ġshould": 921,
+      "Ġits": 922,
+      "ob": 923,
+      "ished": 924,
+      "Ġsurpr": 925,
+      "Ġangry": 926,
+      "Ġfamily": 927,
+      "ress": 928,
+      "igh": 929,
+      "When": 930,
+      "Ġflew": 931,
+      "Ġpeople": 932,
+      "Ġcalled": 933,
+      "No": 934,
+      "Ġred": 935,
+      "Ġstor": 936,
+      "ip": 937,
+      "Ġsoon": 938,
+      "Ġfin": 939,
+      "hn": 940,
+      "Let": 941,
+      "led": 942,
+      "Ġkept": 943,
+      "Ġfore": 944,
+      "fore": 945,
+      "Ġdan": 946,
+      "Ġfly": 947,
+      "Ġshare": 948,
+      "xt": 949,
+      "ised": 950,
+      "dded": 951,
+      "Ġpic": 952,
+      "âĤ¬â": 953,
+      "Ġdoor": 954,
+      "Ġgoing": 955,
+      "ĠP": 956,
+      "ĠWhen": 957,
+      "Ġpretty": 958,
+      "Ġkeep": 959,
+      "Ġrock": 960,
+      "Ġclean": 961,
+      "Ġnow": 962,
+      "Ġdra": 963,
+      "ary": 964,
+      "Ġadvent": 965,
+      "ummy": 966,
+      "Ġnoise": 967,
+      "Ġopened": 968,
+      "Ġshiny": 969,
+      "age": 970,
+      "Ġdoll": 971,
+      "Ġexplore": 972,
+      "Ġwind": 973,
+      "Ġcon": 974,
+      "Ġcry": 975,
+      "Ġide": 976,
+      "Ġbefore": 977,
+      "Ben": 978,
+      "ied": 979,
+      "illy": 980,
+      "Ġreal": 981,
+      "Ġsto": 982,
+      "so": 983,
+      "What": 984,
+      "Ġground": 985,
+      "Ġalso": 986,
+      "les": 987,
+      "Ġturn": 988,
+      "Ħ¢": 989,
+      "âĤ¬âĦ¢": 990,
+      "Ġey": 991,
+      "That": 992,
+      "Ġfar": 993,
+      "Ġidea": 994,
+      "Ġfr": 995,
+      "oon": 996,
+      "Ġnodded": 997,
+      "Ġcolor": 998,
+      "Ġwar": 999
+    },
+    "merges": [
+      [
+        "h",
+        "e"
+      ],
+      [
+        "Ġ",
+        "t"
+      ],
+      [
+        "Ġ",
+        "a"
+      ],
+      [
+        "Ġ",
+        "s"
+      ],
+      [
+        "Ġ",
+        "w"
+      ],
+      [
+        "n",
+        "d"
+      ],
+      [
+        "Ġt",
+        "he"
+      ],
+      [
+        "e",
+        "d"
+      ],
+      [
+        "Ġa",
+        "nd"
+      ],
+      [
+        "Ġt",
+        "o"
+      ],
+      [
+        "Ġ",
+        "b"
+      ],
+      [
+        "i",
+        "n"
+      ],
+      [
+        "Ġ",
+        "h"
+      ],
+      [
+        "Ġw",
+        "a"
+      ],
+      [
+        "r",
+        "e"
+      ],
+      [
+        "o",
+        "u"
+      ],
+      [
+        "Ġ",
+        "f"
+      ],
+      [
+        "i",
+        "t"
+      ],
+      [
+        "Ġ",
+        "l"
+      ],
+      [
+        "Ġ",
+        "c"
+      ],
+      [
+        "Ġ",
+        "d"
+      ],
+      [
+        "e",
+        "r"
+      ],
+      [
+        "Ġ",
+        "he"
+      ],
+      [
+        "Ġ",
+        "m"
+      ],
+      [
+        "Ġ",
+        "p"
+      ],
+      [
+        "Ġwa",
+        "s"
+      ],
+      [
+        "o",
+        "m"
+      ],
+      [
+        "Ġ",
+        "T"
+      ],
+      [
+        "Ġ",
+        "o"
+      ],
+      [
+        "a",
+        "y"
+      ],
+      [
+        "a",
+        "r"
+      ],
+      [
+        "i",
+        "s"
+      ],
+      [
+        "in",
+        "g"
+      ],
+      [
+        "i",
+        "l"
+      ],
+      [
+        "Ġ",
+        "g"
+      ],
+      [
+        "i",
+        "d"
+      ],
+      [
+        "a",
+        "t"
+      ],
+      [
+        "e",
+        "n"
+      ],
+      [
+        "Ġ",
+        "n"
+      ],
+      [
+        "Ġs",
+        "a"
+      ],
+      [
+        "Ġh",
+        "a"
+      ],
+      [
+        "Ġ",
+        "S"
+      ],
+      [
+        "ĠT",
+        "he"
+      ],
+      [
+        "a",
+        "n"
+      ],
+      [
+        "i",
+        "m"
+      ],
+      [
+        "o",
+        "r"
+      ],
+      [
+        "o",
+        "n"
+      ],
+      [
+        "Ġ",
+        "it"
+      ],
+      [
+        "Ġt",
+        "h"
+      ],
+      [
+        "l",
+        "l"
+      ],
+      [
+        "l",
+        "e"
+      ],
+      [
+        "Ġ",
+        "H"
+      ],
+      [
+        "Ġhe",
+        "r"
+      ],
+      [
+        "o",
+        "t"
+      ],
+      [
+        "e",
+        "t"
+      ],
+      [
+        "i",
+        "r"
+      ],
+      [
+        "ĠS",
+        "he"
+      ],
+      [
+        "e",
+        "s"
+      ],
+      [
+        "ĠH",
+        "e"
+      ],
+      [
+        "Ġ",
+        "in"
+      ],
+      [
+        "v",
+        "er"
+      ],
+      [
+        "u",
+        "t"
+      ],
+      [
+        "o",
+        "w"
+      ],
+      [
+        "ĠThe",
+        "y"
+      ],
+      [
+        "c",
+        "k"
+      ],
+      [
+        "Ġ",
+        "e"
+      ],
+      [
+        "Ġ",
+        "u"
+      ],
+      [
+        "l",
+        "d"
+      ],
+      [
+        "Ġ",
+        "y"
+      ],
+      [
+        "o",
+        "o"
+      ],
+      [
+        "Ġsa",
+        "id"
+      ],
+      [
+        "i",
+        "g"
+      ],
+      [
+        "il",
+        "y"
+      ],
+      [
+        "Ġ",
+        "\""
+      ],
+      [
+        "Ġ",
+        "r"
+      ],
+      [
+        "Ġb",
+        "e"
+      ],
+      [
+        "a",
+        "m"
+      ],
+      [
+        "Ġs",
+        "t"
+      ],
+      [
+        "Ġ",
+        "I"
+      ],
+      [
+        "c",
+        "e"
+      ],
+      [
+        "k",
+        "e"
+      ],
+      [
+        "Ġs",
+        "he"
+      ],
+      [
+        "v",
+        "e"
+      ],
+      [
+        "p",
+        "p"
+      ],
+      [
+        "it",
+        "h"
+      ],
+      [
+        "Ġw",
+        "ith"
+      ],
+      [
+        "L",
+        "ily"
+      ],
+      [
+        "O",
+        "n"
+      ],
+      [
+        "Ġo",
+        "n"
+      ],
+      [
+        "Ġy",
+        "ou"
+      ],
+      [
+        "Ġo",
+        "f"
+      ],
+      [
+        "k",
+        "ed"
+      ],
+      [
+        "r",
+        "i"
+      ],
+      [
+        "Ġs",
+        "o"
+      ],
+      [
+        "n",
+        "t"
+      ],
+      [
+        "Ġh",
+        "is"
+      ],
+      [
+        "Ġp",
+        "l"
+      ],
+      [
+        "a",
+        "d"
+      ],
+      [
+        "ver",
+        "y"
+      ],
+      [
+        "Ġd",
+        "ay"
+      ],
+      [
+        "Ġth",
+        "at"
+      ],
+      [
+        "Ġu",
+        "p"
+      ],
+      [
+        "Ġpl",
+        "ay"
+      ],
+      [
+        "Ġha",
+        "d"
+      ],
+      [
+        "s",
+        "t"
+      ],
+      [
+        "Ġthe",
+        "y"
+      ],
+      [
+        "Ġw",
+        "e"
+      ],
+      [
+        "Ġ",
+        "Lily"
+      ],
+      [
+        "Ġm",
+        "om"
+      ],
+      [
+        "Ġf",
+        "or"
+      ],
+      [
+        "Ġ",
+        "B"
+      ],
+      [
+        "e",
+        "l"
+      ],
+      [
+        "u",
+        "n"
+      ],
+      [
+        "ou",
+        "ld"
+      ],
+      [
+        "'",
+        "s"
+      ],
+      [
+        "m",
+        "y"
+      ],
+      [
+        "T",
+        "he"
+      ],
+      [
+        "Ġl",
+        "i"
+      ],
+      [
+        "c",
+        "h"
+      ],
+      [
+        "en",
+        "t"
+      ],
+      [
+        "Ġha",
+        "pp"
+      ],
+      [
+        "Ġwa",
+        "nt"
+      ],
+      [
+        "it",
+        "t"
+      ],
+      [
+        "Ġs",
+        "h"
+      ],
+      [
+        "ou",
+        "t"
+      ],
+      [
+        "he",
+        "r"
+      ],
+      [
+        "Ġd",
+        "o"
+      ],
+      [
+        "l",
+        "y"
+      ],
+      [
+        "Ġn",
+        "ot"
+      ],
+      [
+        "om",
+        "e"
+      ],
+      [
+        "s",
+        "e"
+      ],
+      [
+        "Ġ",
+        "very"
+      ],
+      [
+        "ou",
+        "nd"
+      ],
+      [
+        "e",
+        "nd"
+      ],
+      [
+        "a",
+        "ll"
+      ],
+      [
+        "Ġw",
+        "h"
+      ],
+      [
+        "im",
+        "e"
+      ],
+      [
+        "itt",
+        "le"
+      ],
+      [
+        "Ġ",
+        "k"
+      ],
+      [
+        "Ġt",
+        "ime"
+      ],
+      [
+        "Ġl",
+        "ittle"
+      ],
+      [
+        "a",
+        "l"
+      ],
+      [
+        "Ġ",
+        "Ċ"
+      ],
+      [
+        "Ġthe",
+        "re"
+      ],
+      [
+        "Ġn",
+        "e"
+      ],
+      [
+        "h",
+        "t"
+      ],
+      [
+        "Ġ",
+        "M"
+      ],
+      [
+        "Ġ",
+        "re"
+      ],
+      [
+        "Ġhapp",
+        "y"
+      ],
+      [
+        "Ġs",
+        "m"
+      ],
+      [
+        "Ġb",
+        "ig"
+      ],
+      [
+        "Ġ",
+        "is"
+      ],
+      [
+        "ĠI",
+        "t"
+      ],
+      [
+        "Ġb",
+        "ut"
+      ],
+      [
+        "a",
+        "ck"
+      ],
+      [
+        "Ġa",
+        "n"
+      ],
+      [
+        "Ġsa",
+        "w"
+      ],
+      [
+        "ri",
+        "end"
+      ],
+      [
+        ".",
+        "\""
+      ],
+      [
+        "Ġf",
+        "riend"
+      ],
+      [
+        "r",
+        "y"
+      ],
+      [
+        "Ġa",
+        "s"
+      ],
+      [
+        "r",
+        "a"
+      ],
+      [
+        "On",
+        "e"
+      ],
+      [
+        "id",
+        "e"
+      ],
+      [
+        "a",
+        "ke"
+      ],
+      [
+        "'",
+        "t"
+      ],
+      [
+        "!",
+        "\""
+      ],
+      [
+        "u",
+        "g"
+      ],
+      [
+        "Ġl",
+        "oo"
+      ],
+      [
+        "v",
+        "ed"
+      ],
+      [
+        "t",
+        "er"
+      ],
+      [
+        "Ġwe",
+        "re"
+      ],
+      [
+        "o",
+        "re"
+      ],
+      [
+        "On",
+        "ce"
+      ],
+      [
+        "Ġl",
+        "o"
+      ],
+      [
+        "e",
+        "c"
+      ],
+      [
+        "Ġh",
+        "im"
+      ],
+      [
+        "Ġto",
+        "o"
+      ],
+      [
+        "Ġg",
+        "o"
+      ],
+      [
+        "Ġb",
+        "o"
+      ],
+      [
+        "Ġs",
+        "e"
+      ],
+      [
+        "ir",
+        "l"
+      ],
+      [
+        "Ġa",
+        "re"
+      ],
+      [
+        "Ġ",
+        "j"
+      ],
+      [
+        "ĠT",
+        "im"
+      ],
+      [
+        "ar",
+        "d"
+      ],
+      [
+        "Ġwant",
+        "ed"
+      ],
+      [
+        "il",
+        "l"
+      ],
+      [
+        "Ġg",
+        "irl"
+      ],
+      [
+        "Ġup",
+        "on"
+      ],
+      [
+        "Ġthe",
+        "m"
+      ],
+      [
+        "Ġ",
+        "out"
+      ],
+      [
+        "Ġa",
+        "t"
+      ],
+      [
+        "u",
+        "r"
+      ],
+      [
+        "i",
+        "nd"
+      ],
+      [
+        "Ġthe",
+        "ir"
+      ],
+      [
+        "f",
+        "u"
+      ],
+      [
+        "Ġs",
+        "p"
+      ],
+      [
+        "w",
+        "ay"
+      ],
+      [
+        "Ġ",
+        "A"
+      ],
+      [
+        "Ġsm",
+        "il"
+      ],
+      [
+        "Ġd",
+        "id"
+      ],
+      [
+        "Ġc",
+        "ould"
+      ],
+      [
+        "he",
+        "n"
+      ],
+      [
+        "Ġha",
+        "ve"
+      ],
+      [
+        "a",
+        "in"
+      ],
+      [
+        "ar",
+        "t"
+      ],
+      [
+        "Ġe",
+        "x"
+      ],
+      [
+        "he",
+        "d"
+      ],
+      [
+        "r",
+        "om"
+      ],
+      [
+        "Ġw",
+        "ent"
+      ],
+      [
+        "Ġa",
+        "r"
+      ],
+      [
+        "i",
+        "c"
+      ],
+      [
+        "Ġc",
+        "an"
+      ],
+      [
+        "Ġ",
+        "J"
+      ],
+      [
+        "l",
+        "p"
+      ],
+      [
+        "fu",
+        "l"
+      ],
+      [
+        "ĠB",
+        "en"
+      ],
+      [
+        "oo",
+        "d"
+      ],
+      [
+        "?",
+        "\""
+      ],
+      [
+        "h",
+        "ing"
+      ],
+      [
+        "Ġfriend",
+        "s"
+      ],
+      [
+        "Ġn",
+        "am"
+      ],
+      [
+        "ig",
+        "ht"
+      ],
+      [
+        "Ġa",
+        "ll"
+      ],
+      [
+        "Ġhe",
+        "lp"
+      ],
+      [
+        "Ġk",
+        "n"
+      ],
+      [
+        "u",
+        "m"
+      ],
+      [
+        "ar",
+        "k"
+      ],
+      [
+        "on",
+        "e"
+      ],
+      [
+        "Ġb",
+        "ack"
+      ],
+      [
+        "Ġs",
+        "ay"
+      ],
+      [
+        "Y",
+        "ou"
+      ],
+      [
+        "Ġf",
+        "un"
+      ],
+      [
+        "Ġc",
+        "l"
+      ],
+      [
+        "ĠT",
+        "om"
+      ],
+      [
+        "a",
+        "re"
+      ],
+      [
+        "Ġn",
+        "o"
+      ],
+      [
+        "Ġl",
+        "e"
+      ],
+      [
+        "o",
+        "p"
+      ],
+      [
+        "Ġsmil",
+        "ed"
+      ],
+      [
+        "Ġs",
+        "c"
+      ],
+      [
+        "Ġnam",
+        "ed"
+      ],
+      [
+        "Ġa",
+        "l"
+      ],
+      [
+        "ou",
+        "g"
+      ],
+      [
+        "Ġlo",
+        "ved"
+      ],
+      [
+        "s",
+        "ide"
+      ],
+      [
+        "el",
+        "t"
+      ],
+      [
+        "Ġ",
+        "One"
+      ],
+      [
+        "Ġm",
+        "an"
+      ],
+      [
+        "Ġas",
+        "ked"
+      ],
+      [
+        "i",
+        "ck"
+      ],
+      [
+        "Ġto",
+        "y"
+      ],
+      [
+        "Ġli",
+        "ke"
+      ],
+      [
+        "Ġf",
+        "e"
+      ],
+      [
+        "Ġf",
+        "elt"
+      ],
+      [
+        "Ġloo",
+        "ked"
+      ],
+      [
+        "Ġs",
+        "ome"
+      ],
+      [
+        "Ġse",
+        "e"
+      ],
+      [
+        "Ġar",
+        "ound"
+      ],
+      [
+        "Ġm",
+        "e"
+      ],
+      [
+        "am",
+        "e"
+      ],
+      [
+        "om",
+        "et"
+      ],
+      [
+        "Ġ",
+        "W"
+      ],
+      [
+        "Ġr",
+        "o"
+      ],
+      [
+        "Ġb",
+        "r"
+      ],
+      [
+        "u",
+        "re"
+      ],
+      [
+        "ĠTim",
+        "my"
+      ],
+      [
+        "Ġb",
+        "ir"
+      ],
+      [
+        "g",
+        "et"
+      ],
+      [
+        "i",
+        "ce"
+      ],
+      [
+        "Ġbo",
+        "y"
+      ],
+      [
+        "Ġw",
+        "ould"
+      ],
+      [
+        "Ġst",
+        "art"
+      ],
+      [
+        "on",
+        "g"
+      ],
+      [
+        "Ã",
+        "¢"
+      ],
+      [
+        "â",
+        "Ĥ"
+      ],
+      [
+        "âĤ",
+        "¬"
+      ],
+      [
+        "s",
+        "s"
+      ],
+      [
+        "Ġbir",
+        "d"
+      ],
+      [
+        "Ġs",
+        "omet"
+      ],
+      [
+        "Ġf",
+        "a"
+      ],
+      [
+        "d",
+        "d"
+      ],
+      [
+        "ing",
+        "s"
+      ],
+      [
+        "Ġa",
+        "g"
+      ],
+      [
+        "Ġw",
+        "or"
+      ],
+      [
+        "Ġwh",
+        "at"
+      ],
+      [
+        "ad",
+        "e"
+      ],
+      [
+        "Ġm",
+        "ake"
+      ],
+      [
+        "k",
+        "ing"
+      ],
+      [
+        ",",
+        "\""
+      ],
+      [
+        "i",
+        "e"
+      ],
+      [
+        "ĠB",
+        "ut"
+      ],
+      [
+        "ow",
+        "n"
+      ],
+      [
+        "Ġt",
+        "re"
+      ],
+      [
+        "Ġr",
+        "an"
+      ],
+      [
+        "get",
+        "her"
+      ],
+      [
+        "Ġ",
+        "You"
+      ],
+      [
+        "Ġa",
+        "way"
+      ],
+      [
+        "a",
+        "g"
+      ],
+      [
+        "ar",
+        "ed"
+      ],
+      [
+        "Ġsay",
+        "s"
+      ],
+      [
+        "Ġstart",
+        "ed"
+      ],
+      [
+        "ou",
+        "d"
+      ],
+      [
+        "i",
+        "f"
+      ],
+      [
+        "Ġm",
+        "ade"
+      ],
+      [
+        "Ġc",
+        "ar"
+      ],
+      [
+        "Ġsomet",
+        "hing"
+      ],
+      [
+        "Ġto",
+        "gether"
+      ],
+      [
+        "it",
+        "ed"
+      ],
+      [
+        "t",
+        "her"
+      ],
+      [
+        "Ġp",
+        "ark"
+      ],
+      [
+        "Ġc",
+        "o"
+      ],
+      [
+        "Ġsa",
+        "d"
+      ],
+      [
+        "Ġo",
+        "ther"
+      ],
+      [
+        "Ġne",
+        "w"
+      ],
+      [
+        "Ġex",
+        "c"
+      ],
+      [
+        "Ġp",
+        "ut"
+      ],
+      [
+        "Ġf",
+        "rom"
+      ],
+      [
+        "Ġp",
+        "r"
+      ],
+      [
+        "e",
+        "ll"
+      ],
+      [
+        "Ġ",
+        "L"
+      ],
+      [
+        "Ġl",
+        "a"
+      ],
+      [
+        "Ġh",
+        "ug"
+      ],
+      [
+        "b",
+        "le"
+      ],
+      [
+        "oo",
+        "k"
+      ],
+      [
+        "Ġm",
+        "u"
+      ],
+      [
+        "a",
+        "ch"
+      ],
+      [
+        "Ġag",
+        "ain"
+      ],
+      [
+        "Ġh",
+        "ome"
+      ],
+      [
+        "Ġw",
+        "hen"
+      ],
+      [
+        "Ġg",
+        "ood"
+      ],
+      [
+        "e",
+        "p"
+      ],
+      [
+        "h",
+        "at"
+      ],
+      [
+        "Ġwh",
+        "o"
+      ],
+      [
+        "es",
+        "t"
+      ],
+      [
+        "ri",
+        "ed"
+      ],
+      [
+        "Ġf",
+        "ound"
+      ],
+      [
+        "Ġf",
+        "l"
+      ],
+      [
+        "Ġthe",
+        "n"
+      ],
+      [
+        "Ġc",
+        "h"
+      ],
+      [
+        "Ġd",
+        "ec"
+      ],
+      [
+        "pp",
+        "ed"
+      ],
+      [
+        "Ġwa",
+        "l"
+      ],
+      [
+        "a",
+        "s"
+      ],
+      [
+        "Ġg",
+        "et"
+      ],
+      [
+        "q",
+        "u"
+      ],
+      [
+        "Ġplay",
+        "ing"
+      ],
+      [
+        "oug",
+        "ht"
+      ],
+      [
+        "p",
+        "l"
+      ],
+      [
+        "Ġ",
+        "E"
+      ],
+      [
+        "all",
+        "y"
+      ],
+      [
+        "Ġs",
+        "w"
+      ],
+      [
+        "ou",
+        "s"
+      ],
+      [
+        "n",
+        "n"
+      ],
+      [
+        "Ġth",
+        "ings"
+      ],
+      [
+        "Ġexc",
+        "ited"
+      ],
+      [
+        "Ġli",
+        "ked"
+      ],
+      [
+        "Ġg",
+        "ot"
+      ],
+      [
+        "u",
+        "ck"
+      ],
+      [
+        "r",
+        "o"
+      ],
+      [
+        "id",
+        "ed"
+      ],
+      [
+        "Ġdec",
+        "ided"
+      ],
+      [
+        "Ġb",
+        "l"
+      ],
+      [
+        "a",
+        "ve"
+      ],
+      [
+        "Ġc",
+        "ame"
+      ],
+      [
+        "Ġe",
+        "very"
+      ],
+      [
+        "ar",
+        "a"
+      ],
+      [
+        "ĠM",
+        "om"
+      ],
+      [
+        "Ġyou",
+        "r"
+      ],
+      [
+        "Ġ",
+        "D"
+      ],
+      [
+        "a",
+        "x"
+      ],
+      [
+        "Ġ",
+        "v"
+      ],
+      [
+        "Ġsc",
+        "ared"
+      ],
+      [
+        "u",
+        "st"
+      ],
+      [
+        "Ġon",
+        "e"
+      ],
+      [
+        "Ġdo",
+        "g"
+      ],
+      [
+        "Ġd",
+        "own"
+      ],
+      [
+        "ou",
+        "se"
+      ],
+      [
+        "n",
+        "y"
+      ],
+      [
+        "Ġf",
+        "ind"
+      ],
+      [
+        "Ġc",
+        "are"
+      ],
+      [
+        "Ġbe",
+        "c"
+      ],
+      [
+        "is",
+        "t"
+      ],
+      [
+        "Ġth",
+        "an"
+      ],
+      [
+        "Ġfe",
+        "el"
+      ],
+      [
+        "a",
+        "p"
+      ],
+      [
+        "u",
+        "e"
+      ],
+      [
+        "u",
+        "dd"
+      ],
+      [
+        "nn",
+        "a"
+      ],
+      [
+        "Ġd",
+        "ad"
+      ],
+      [
+        "Ġa",
+        "b"
+      ],
+      [
+        "The",
+        "y"
+      ],
+      [
+        "Ġm",
+        "y"
+      ],
+      [
+        "Ġloo",
+        "k"
+      ],
+      [
+        "Ġ",
+        "ke"
+      ],
+      [
+        "ou",
+        "r"
+      ],
+      [
+        "Ġw",
+        "ill"
+      ],
+      [
+        "ar",
+        "n"
+      ],
+      [
+        "Ġg",
+        "r"
+      ],
+      [
+        "u",
+        "s"
+      ],
+      [
+        "nd",
+        "er"
+      ],
+      [
+        "Ġg",
+        "ra"
+      ],
+      [
+        "way",
+        "s"
+      ],
+      [
+        "es",
+        "s"
+      ],
+      [
+        "Ġdid",
+        "n"
+      ],
+      [
+        "Ġp",
+        "o"
+      ],
+      [
+        "f",
+        "e"
+      ],
+      [
+        "Ġal",
+        "ways"
+      ],
+      [
+        "Ġtoo",
+        "k"
+      ],
+      [
+        "Ġab",
+        "out"
+      ],
+      [
+        "an",
+        "t"
+      ],
+      [
+        "b",
+        "b"
+      ],
+      [
+        "Ġmom",
+        "my"
+      ],
+      [
+        "Ġl",
+        "ot"
+      ],
+      [
+        "Ġtoy",
+        "s"
+      ],
+      [
+        "Ġkn",
+        "e"
+      ],
+      [
+        "er",
+        "s"
+      ],
+      [
+        "is",
+        "e"
+      ],
+      [
+        "it",
+        "e"
+      ],
+      [
+        "Ġout",
+        "side"
+      ],
+      [
+        "Ġtre",
+        "e"
+      ],
+      [
+        "Ġth",
+        "ought"
+      ],
+      [
+        "Ġb",
+        "all"
+      ],
+      [
+        "Ġ",
+        "F"
+      ],
+      [
+        "Ġm",
+        "ore"
+      ],
+      [
+        "ec",
+        "i"
+      ],
+      [
+        "ĠS",
+        "am"
+      ],
+      [
+        "en",
+        "ed"
+      ],
+      [
+        "c",
+        "hed"
+      ],
+      [
+        "Ġt",
+        "a"
+      ],
+      [
+        "Ġo",
+        "ld"
+      ],
+      [
+        "Ġh",
+        "o"
+      ],
+      [
+        "Ġle",
+        "arn"
+      ],
+      [
+        "re",
+        "t"
+      ],
+      [
+        "Ġin",
+        "t"
+      ],
+      [
+        "g",
+        "ed"
+      ],
+      [
+        "Ġkn",
+        "ow"
+      ],
+      [
+        "Ġla",
+        "ug"
+      ],
+      [
+        "Ġt",
+        "ake"
+      ],
+      [
+        "eci",
+        "al"
+      ],
+      [
+        "Ġs",
+        "or"
+      ],
+      [
+        "Ġsp",
+        "ecial"
+      ],
+      [
+        "Ġc",
+        "at"
+      ],
+      [
+        "udd",
+        "en"
+      ],
+      [
+        "Ġkne",
+        "w"
+      ],
+      [
+        "ĠM",
+        "ax"
+      ],
+      [
+        "i",
+        "ve"
+      ],
+      [
+        "i",
+        "a"
+      ],
+      [
+        "Ġp",
+        "e"
+      ],
+      [
+        "Ġan",
+        "y"
+      ],
+      [
+        "udden",
+        "ly"
+      ],
+      [
+        "Ġt",
+        "r"
+      ],
+      [
+        "f",
+        "ter"
+      ],
+      [
+        "Ġh",
+        "ow"
+      ],
+      [
+        "m",
+        "a"
+      ],
+      [
+        "Ġsh",
+        "ow"
+      ],
+      [
+        "in",
+        "k"
+      ],
+      [
+        "Ġsor",
+        "ry"
+      ],
+      [
+        "Ġt",
+        "w"
+      ],
+      [
+        "B",
+        "ut"
+      ],
+      [
+        "Ġmu",
+        "ch"
+      ],
+      [
+        "a",
+        "u"
+      ],
+      [
+        "Ġr",
+        "un"
+      ],
+      [
+        "is",
+        "h"
+      ],
+      [
+        "a",
+        "nd"
+      ],
+      [
+        "Ġha",
+        "nd"
+      ],
+      [
+        "Ġs",
+        "l"
+      ],
+      [
+        "v",
+        "en"
+      ],
+      [
+        "Ġh",
+        "ouse"
+      ],
+      [
+        "Ġo",
+        "r"
+      ],
+      [
+        "Ġo",
+        "p"
+      ],
+      [
+        "Ġs",
+        "k"
+      ],
+      [
+        "Ġm",
+        "o"
+      ],
+      [
+        "Ġcl",
+        "o"
+      ],
+      [
+        "Ġs",
+        "un"
+      ],
+      [
+        "Ġint",
+        "o"
+      ],
+      [
+        "Ġt",
+        "ried"
+      ],
+      [
+        "Ġin",
+        "side"
+      ],
+      [
+        "at",
+        "e"
+      ],
+      [
+        "Ġto",
+        "ld"
+      ],
+      [
+        "Ġwa",
+        "ter"
+      ],
+      [
+        "Ġth",
+        "is"
+      ],
+      [
+        "an",
+        "k"
+      ],
+      [
+        "Ġ",
+        "en"
+      ],
+      [
+        "Ġ",
+        "if"
+      ],
+      [
+        "Ġpr",
+        "oud"
+      ],
+      [
+        "um",
+        "p"
+      ],
+      [
+        "Ġ",
+        "qu"
+      ],
+      [
+        "Ġo",
+        "ver"
+      ],
+      [
+        "T",
+        "om"
+      ],
+      [
+        "Ġcould",
+        "n"
+      ],
+      [
+        "d",
+        "y"
+      ],
+      [
+        "Ġg",
+        "ave"
+      ],
+      [
+        "Ġhe",
+        "ard"
+      ],
+      [
+        "ĠS",
+        "ara"
+      ],
+      [
+        "Ġne",
+        "ver"
+      ],
+      [
+        "b",
+        "y"
+      ],
+      [
+        "Ġe",
+        "ach"
+      ],
+      [
+        "a",
+        "ce"
+      ],
+      [
+        "Ġro",
+        "om"
+      ],
+      [
+        "t",
+        "y"
+      ],
+      [
+        "Ġex",
+        "pl"
+      ],
+      [
+        "ĠE",
+        "very"
+      ],
+      [
+        "Ġe",
+        "at"
+      ],
+      [
+        "ĠW",
+        "e"
+      ],
+      [
+        "ot",
+        "her"
+      ],
+      [
+        "au",
+        "se"
+      ],
+      [
+        "Ġp",
+        "ick"
+      ],
+      [
+        "i",
+        "on"
+      ],
+      [
+        "Ġp",
+        "ret"
+      ],
+      [
+        "ĠA",
+        "nna"
+      ],
+      [
+        "M",
+        "om"
+      ],
+      [
+        "Ġplay",
+        "ed"
+      ],
+      [
+        "g",
+        "e"
+      ],
+      [
+        "et",
+        "ter"
+      ],
+      [
+        "Ġj",
+        "ust"
+      ],
+      [
+        "a",
+        "k"
+      ],
+      [
+        "Ġhug",
+        "ged"
+      ],
+      [
+        "Ġg",
+        "re"
+      ],
+      [
+        "he",
+        "re"
+      ],
+      [
+        "Ġof",
+        "f"
+      ],
+      [
+        "Ġc",
+        "om"
+      ],
+      [
+        "Ġwa",
+        "t"
+      ],
+      [
+        "ot",
+        "h"
+      ],
+      [
+        "Ġbo",
+        "x"
+      ],
+      [
+        "Ġn",
+        "ice"
+      ],
+      [
+        "'",
+        "m"
+      ],
+      [
+        "Ġst",
+        "r"
+      ],
+      [
+        "Ġne",
+        "ed"
+      ],
+      [
+        "Ġbec",
+        "ause"
+      ],
+      [
+        "il",
+        "e"
+      ],
+      [
+        "Ġman",
+        "y"
+      ],
+      [
+        "Ġf",
+        "o"
+      ],
+      [
+        "u",
+        "c"
+      ],
+      [
+        "Ġj",
+        "o"
+      ],
+      [
+        "Ġbe",
+        "ar"
+      ],
+      [
+        "Ġsm",
+        "all"
+      ],
+      [
+        "i",
+        "z"
+      ],
+      [
+        "Ġb",
+        "u"
+      ],
+      [
+        "v",
+        "ing"
+      ],
+      [
+        "Ġl",
+        "ong"
+      ],
+      [
+        "in",
+        "e"
+      ],
+      [
+        "g",
+        "ry"
+      ],
+      [
+        "im",
+        "al"
+      ],
+      [
+        "or",
+        "t"
+      ],
+      [
+        "Ġan",
+        "imal"
+      ],
+      [
+        "Ġs",
+        "n"
+      ],
+      [
+        "oug",
+        "h"
+      ],
+      [
+        "Ġt",
+        "ry"
+      ],
+      [
+        "Ġu",
+        "nt"
+      ],
+      [
+        "il",
+        "d"
+      ],
+      [
+        "s",
+        "el"
+      ],
+      [
+        "ur",
+        "t"
+      ],
+      [
+        "Ġunt",
+        "il"
+      ],
+      [
+        "ĠJ",
+        "ack"
+      ],
+      [
+        "s",
+        "ed"
+      ],
+      [
+        "Ġlearn",
+        "ed"
+      ],
+      [
+        "Ġk",
+        "ind"
+      ],
+      [
+        "Ġ",
+        "im"
+      ],
+      [
+        "Ġlo",
+        "ve"
+      ],
+      [
+        "Ġb",
+        "etter"
+      ],
+      [
+        "f",
+        "t"
+      ],
+      [
+        "Ġc",
+        "all"
+      ],
+      [
+        "Ġfl",
+        "ow"
+      ],
+      [
+        "Ġd",
+        "on"
+      ],
+      [
+        "H",
+        "e"
+      ],
+      [
+        "ĠJ",
+        "o"
+      ],
+      [
+        "Ġe",
+        "nd"
+      ],
+      [
+        "Ġa",
+        "d"
+      ],
+      [
+        "u",
+        "ll"
+      ],
+      [
+        "Ġb",
+        "est"
+      ],
+      [
+        "v",
+        "ent"
+      ],
+      [
+        "Y",
+        "es"
+      ],
+      [
+        "ar",
+        "s"
+      ],
+      [
+        "ur",
+        "p"
+      ],
+      [
+        "ad",
+        "y"
+      ],
+      [
+        "e",
+        "m"
+      ],
+      [
+        "re",
+        "am"
+      ],
+      [
+        "a",
+        "ut"
+      ],
+      [
+        "ur",
+        "n"
+      ],
+      [
+        "ĠM",
+        "ia"
+      ],
+      [
+        "Ġc",
+        "le"
+      ],
+      [
+        "ĠA",
+        "nd"
+      ],
+      [
+        "v",
+        "es"
+      ],
+      [
+        "Å",
+        "ĵ"
+      ],
+      [
+        "Ġ",
+        "C"
+      ],
+      [
+        "ard",
+        "en"
+      ],
+      [
+        "Ġg",
+        "arden"
+      ],
+      [
+        "Ġfa",
+        "st"
+      ],
+      [
+        "b",
+        "er"
+      ],
+      [
+        "Ġcare",
+        "ful"
+      ],
+      [
+        "Ġbe",
+        "aut"
+      ],
+      [
+        "ll",
+        "y"
+      ],
+      [
+        "T",
+        "h"
+      ],
+      [
+        "Ġe",
+        "ven"
+      ],
+      [
+        "p",
+        "t"
+      ],
+      [
+        "Ġb",
+        "ra"
+      ],
+      [
+        "i",
+        "es"
+      ],
+      [
+        "Ġthan",
+        "ked"
+      ],
+      [
+        "Ġf",
+        "i"
+      ],
+      [
+        "ĠS",
+        "o"
+      ],
+      [
+        "Ġc",
+        "he"
+      ],
+      [
+        "Ġlaug",
+        "hed"
+      ],
+      [
+        "Ġsk",
+        "y"
+      ],
+      [
+        "Ġb",
+        "y"
+      ],
+      [
+        "I",
+        "t"
+      ],
+      [
+        "ĠH",
+        "er"
+      ],
+      [
+        "Ġj",
+        "ump"
+      ],
+      [
+        "Ġg",
+        "l"
+      ],
+      [
+        "a",
+        "se"
+      ],
+      [
+        "Ġt",
+        "e"
+      ],
+      [
+        "Ġl",
+        "oud"
+      ],
+      [
+        "sel",
+        "f"
+      ],
+      [
+        "in",
+        "y"
+      ],
+      [
+        "Ġwa",
+        "y"
+      ],
+      [
+        "w",
+        "n"
+      ],
+      [
+        "Ġbeaut",
+        "i"
+      ],
+      [
+        "Ġc",
+        "ome"
+      ],
+      [
+        "le",
+        "w"
+      ],
+      [
+        "Ġl",
+        "ist"
+      ],
+      [
+        "Ġw",
+        "o"
+      ],
+      [
+        "Ġbeauti",
+        "ful"
+      ],
+      [
+        "Ġh",
+        "ard"
+      ],
+      [
+        "Ġlot",
+        "s"
+      ],
+      [
+        "Ġr",
+        "a"
+      ],
+      [
+        "Ġst",
+        "ill"
+      ],
+      [
+        "Ġf",
+        "am"
+      ],
+      [
+        "Ġanimal",
+        "s"
+      ],
+      [
+        "Ġ",
+        "â"
+      ],
+      [
+        "Ġh",
+        "urt"
+      ],
+      [
+        "Ġu",
+        "nder"
+      ],
+      [
+        "ĠThe",
+        "n"
+      ],
+      [
+        "ec",
+        "t"
+      ],
+      [
+        "Ġst",
+        "ay"
+      ],
+      [
+        "n",
+        "ing"
+      ],
+      [
+        "Ġl",
+        "et"
+      ],
+      [
+        "c",
+        "t"
+      ],
+      [
+        "Ġb",
+        "oth"
+      ],
+      [
+        "Ġc",
+        "u"
+      ],
+      [
+        "ĠH",
+        "is"
+      ],
+      [
+        "he",
+        "s"
+      ],
+      [
+        "b",
+        "e"
+      ],
+      [
+        "Ġsa",
+        "fe"
+      ],
+      [
+        "ĠF",
+        "rom"
+      ],
+      [
+        "oo",
+        "l"
+      ],
+      [
+        "re",
+        "e"
+      ],
+      [
+        "Ġco",
+        "l"
+      ],
+      [
+        "Ġtw",
+        "o"
+      ],
+      [
+        "Ġb",
+        "ad"
+      ],
+      [
+        "Ġb",
+        "ook"
+      ],
+      [
+        "Ġim",
+        "p"
+      ],
+      [
+        "Ġre",
+        "m"
+      ],
+      [
+        "op",
+        "le"
+      ],
+      [
+        "an",
+        "e"
+      ],
+      [
+        "Ġli",
+        "ved"
+      ],
+      [
+        "k",
+        "ay"
+      ],
+      [
+        "o",
+        "ck"
+      ],
+      [
+        "uc",
+        "y"
+      ],
+      [
+        "Ġwal",
+        "ked"
+      ],
+      [
+        "T",
+        "im"
+      ],
+      [
+        "a",
+        "st"
+      ],
+      [
+        "urp",
+        "r"
+      ],
+      [
+        "Ġbra",
+        "ve"
+      ],
+      [
+        "Ġsh",
+        "ould"
+      ],
+      [
+        "Ġit",
+        "s"
+      ],
+      [
+        "o",
+        "b"
+      ],
+      [
+        "is",
+        "hed"
+      ],
+      [
+        "Ġs",
+        "urpr"
+      ],
+      [
+        "Ġan",
+        "gry"
+      ],
+      [
+        "Ġfam",
+        "ily"
+      ],
+      [
+        "re",
+        "ss"
+      ],
+      [
+        "ig",
+        "h"
+      ],
+      [
+        "W",
+        "hen"
+      ],
+      [
+        "Ġf",
+        "lew"
+      ],
+      [
+        "Ġpe",
+        "ople"
+      ],
+      [
+        "Ġcall",
+        "ed"
+      ],
+      [
+        "N",
+        "o"
+      ],
+      [
+        "Ġr",
+        "ed"
+      ],
+      [
+        "Ġst",
+        "or"
+      ],
+      [
+        "i",
+        "p"
+      ],
+      [
+        "Ġso",
+        "on"
+      ],
+      [
+        "Ġf",
+        "in"
+      ],
+      [
+        "h",
+        "n"
+      ],
+      [
+        "L",
+        "et"
+      ],
+      [
+        "l",
+        "ed"
+      ],
+      [
+        "Ġke",
+        "pt"
+      ],
+      [
+        "Ġf",
+        "ore"
+      ],
+      [
+        "f",
+        "ore"
+      ],
+      [
+        "Ġd",
+        "an"
+      ],
+      [
+        "Ġf",
+        "ly"
+      ],
+      [
+        "Ġsh",
+        "are"
+      ],
+      [
+        "x",
+        "t"
+      ],
+      [
+        "is",
+        "ed"
+      ],
+      [
+        "dd",
+        "ed"
+      ],
+      [
+        "Ġp",
+        "ic"
+      ],
+      [
+        "âĤ¬",
+        "â"
+      ],
+      [
+        "Ġdo",
+        "or"
+      ],
+      [
+        "Ġgo",
+        "ing"
+      ],
+      [
+        "Ġ",
+        "P"
+      ],
+      [
+        "ĠW",
+        "hen"
+      ],
+      [
+        "Ġpret",
+        "ty"
+      ],
+      [
+        "Ġke",
+        "ep"
+      ],
+      [
+        "Ġro",
+        "ck"
+      ],
+      [
+        "Ġcle",
+        "an"
+      ],
+      [
+        "Ġn",
+        "ow"
+      ],
+      [
+        "Ġd",
+        "ra"
+      ],
+      [
+        "ar",
+        "y"
+      ],
+      [
+        "Ġad",
+        "vent"
+      ],
+      [
+        "um",
+        "my"
+      ],
+      [
+        "Ġno",
+        "ise"
+      ],
+      [
+        "Ġop",
+        "ened"
+      ],
+      [
+        "Ġsh",
+        "iny"
+      ],
+      [
+        "ag",
+        "e"
+      ],
+      [
+        "Ġdo",
+        "ll"
+      ],
+      [
+        "Ġexpl",
+        "ore"
+      ],
+      [
+        "Ġw",
+        "ind"
+      ],
+      [
+        "Ġc",
+        "on"
+      ],
+      [
+        "Ġc",
+        "ry"
+      ],
+      [
+        "Ġ",
+        "ide"
+      ],
+      [
+        "Ġbe",
+        "fore"
+      ],
+      [
+        "B",
+        "en"
+      ],
+      [
+        "i",
+        "ed"
+      ],
+      [
+        "il",
+        "ly"
+      ],
+      [
+        "Ġre",
+        "al"
+      ],
+      [
+        "Ġst",
+        "o"
+      ],
+      [
+        "s",
+        "o"
+      ],
+      [
+        "W",
+        "hat"
+      ],
+      [
+        "Ġgr",
+        "ound"
+      ],
+      [
+        "Ġal",
+        "so"
+      ],
+      [
+        "le",
+        "s"
+      ],
+      [
+        "Ġt",
+        "urn"
+      ],
+      [
+        "Ħ",
+        "¢"
+      ],
+      [
+        "âĤ¬â",
+        "Ħ¢"
+      ],
+      [
+        "Ġe",
+        "y"
+      ],
+      [
+        "T",
+        "hat"
+      ],
+      [
+        "Ġf",
+        "ar"
+      ],
+      [
+        "Ġide",
+        "a"
+      ],
+      [
+        "Ġf",
+        "r"
+      ],
+      [
+        "o",
+        "on"
+      ],
+      [
+        "Ġno",
+        "dded"
+      ],
+      [
+        "Ġcol",
+        "or"
+      ],
+      [
+        "Ġwa",
+        "r"
+      ]
+    ]
+  }
+}

hf/tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<|im_start|>"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "tokenizer_class": "TokenizersBackend"
+}

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers>=5.14.1
+huggingface_hub