初始化项目，由ModelHub XC社区提供模型

Model: Tonic/GemmaX2-28-2B-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,40 @@
+*.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
+gemmax2-28-2b-f16.gguf filter=lfs diff=lfs merge=lfs -text
+gemmax2-28-2b-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+gemmax2-28-2b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemmax2-28-2b-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemmax2-28-2b-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,186 @@
+---
+license: apache-2.0
+language:
+- ar
+- bn
+- cs
+- de
+- en
+- es
+- fa
+- fr
+- he
+- hi
+- id
+- it
+- ja
+- km
+- ko
+- lo
+- ms
+- my
+- nl
+- pl
+- pt
+- ru
+- th
+- tl
+- tk
+- ur
+- vi
+- zh
+base_model:
+- ModelSpace/GemmaX2-28-2B-v0.1
+pipeline_tag: translation
+library_name: transformers
+tags:
+- gemma
+- translation
+- multilingual
+- quantized
+metrics:
+- bleu
+- rouge
+model-index:
+  - name: GemmaX2-28-2B-gguf
+    results:
+      - task:
+          type: translation
+        dataset:
+          name: google/smol
+          type: translation
+        metrics:
+          - name: ROUGE
+            type: translate
+            value: 0.6230
+        source:
+          name: self-eval
+          url: https://huggingface.co/Tonic/GemmaX2-28-2B-gguf/blob/main/results_en_es_1740935448.json
+  - name: GemmaX2-28-2B-gguf
+    results:
+      - task:
+          type: translation
+        dataset:
+          name: google/smol
+          type: translation
+        metrics:
+          - name: BLEU
+            type: translate
+            value: 0.6358
+        source:
+          name: self-eval
+          url: https://huggingface.co/Tonic/GemmaX2-28-2B-gguf/blob/main/results_en_es_1740935448.json
+---
+# Model Card for GemmaX2-28-2B GGUF Quantizations
+
+## Model Overview
+
+**GemmaX2-28-2B GGUF Quantizations** are a set of quantized variants of `GemmaX2-28-2B-v0.1`, an LLM-based translation model developed by Xiaomi. The original model was finetuned from `GemmaX2-28-2B-Pretrain`, which itself is a continually pretrained version of `Gemma2-2B` using a diverse dataset of 56 billion tokens across 28 languages. These GGUF versions (`f16`, `bf16`, `q8_0`, `tq1_0`, `tq2_0`) were created to optimize the model for efficient inference on resource-constrained environments while preserving translation capabilities.
+
+- **Developed by**: Xiaomi (original model); quantized by Tonic
+- **Model Type**: Transformer-based language model, finetuned for translation, quantized to GGUF format
+- **Quantization Formats**: `f16` (16-bit float), `bf16` (bfloat16), `q8_0` (8-bit quantization), `tq1_0` (ternary quantization 1), `tq2_0` (ternary quantization 2)
+- **Languages**: Arabic, Bengali, Czech, German, English, Spanish, Persian, French, Hebrew, Hindi, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Burmese, Dutch, Polish, Portuguese, Russian, Thai, Tagalog, Turkish, Urdu, Vietnamese, Chinese
+- **License**: [Apache 2.0]
+- **Repository**: [Tonic/GemmaX2-28-2B-gguf](https://huggingface.co/Tonic/GemmaX2-28-2B-gguf)
+
+## Model Description
+
+`GemmaX2-28-2B-v0.1` is designed for multilingual machine translation, built on `GemmaX2-28-2B-Pretrain`, which was pretrained on a mix of monolingual and parallel data (56 billion tokens) across 28 languages. The finetuning process used a small, high-quality set of translation instruction data to enhance its performance. These GGUF quantizations were generated using `convert_hf_to_gguf.py`, converting the original Hugging Face model into formats compatible with tools like `llama.cpp` for efficient deployment.
+
+### Quantization Details
+- **Source Model**: `ModelSpace/GemmaX2-28-2B-v0.1`
+- **Conversion Tool**: `convert_hf_to_gguf.py`
+- **Quantization Types**:
+  - `f16`: 16-bit floating-point, minimal precision loss, larger file size (~5-7GB).
+  - `bf16`: Brain floating-point 16-bit, optimized for certain hardware (e.g., TPUs), similar size to `f16`.
+  - `q8_0`: 8-bit quantization, reduced size (~3-4GB), slight precision trade-off.
+  - `tq1_0`: Ternary quantization (1-bit), smallest size (~1-2GB), higher precision loss.
+  - `tq2_0`: Ternary quantization (2-bit variant), slightly larger than `tq1_0`, balanced size vs. quality.
+
+## Intended Use
+
+These quantized models are intended for:
+- **Multilingual Translation**: Translating text across the 28 supported languages.
+- **Efficient Inference**: Deployment on edge devices, low-memory systems, or environments with limited compute resources using GGUF-compatible frameworks (e.g., `llama.cpp`).
+- **Research**: Studying the trade-offs between quantization levels and translation performance.
+
+### Use Cases
+- Real-time translation applications.
+- Offline translation on mobile or embedded devices.
+- Benchmarking quantized LLM performance in multilingual settings.
+
+## Model Performance
+
+The original `GemmaX2-28-2B-v0.1` model’s performance is detailed in the paper [Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study](https://arxiv.org/abs/2502.02481). Quantization introduces varying degrees of performance trade-offs:
+- **`f16` and `bf16`**: Near-identical to the original model’s accuracy, with minimal degradation.
+- **`q8_0`**: Slight reduction in translation quality, still suitable for most practical applications.
+- **`tq1_0` and `tq2_0`**: Noticeable quality loss, best for scenarios prioritizing speed and size over precision.
+
+Exact metrics depend on the downstream task and dataset; users are encouraged to evaluate performance for their specific use case.
+
+## How to Use
+
+### With Transformers (Original Model)
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "ModelSpace/GemmaX2-28-2B-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+text = "Translate this from Chinese to English:\nChinese: 我爱机器翻译\nEnglish:"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+### With GGUF (Quantized Models)
+Download a GGUF file from `Tonic/GemmaX2-28-2B-gguf` and use it with a GGUF-compatible inference tool like `llama.cpp`:
+
+```bash
+# Example with llama.cpp
+git clone https://github.com/ggerganov/llama.cpp.git
+cd llama.cpp
+make
+
+# Run inference with q8_0 model
+./main -m gemmax2-28-2b-q8_0.gguf -p "Translate from Chinese to English: 我爱机器翻译\nEnglish:""
+```
+
+Available files:
+- `gemmax2-28-2b-f16.gguf`
+- `gemmax2-28-2b-bf16.gguf`
+- `gemmax2-28-2b-q8_0.gguf`
+- `gemmax2-28-2b-tq1_0.gguf`
+- `gemmax2-28-2b-tq2_0.gguf`
+
+## Limitations
+
+- **Language Support**: Only supports the 28 languages listed above; performance on unsupported languages is not guaranteed.
+- **Quantization Trade-offs**: Lower-bit quantizations (`tq1_0`, `tq2_0`) may degrade translation quality, especially for complex sentences or rare language pairs.
+- **Hardware Compatibility**: `bf16` benefits from specific hardware support (e.g., NVIDIA Ampere GPUs, TPUs); performance may vary otherwise.
+- **Future Improvements**: The original authors plan to enhance `GemmaX2-28-2B`’s translation capabilities, which may not be reflected in these quantized versions until updated.
+
+## Citation
+
+For the original model:
+```bibtex
+@misc{cui2025multilingualmachinetranslationopen,
+  title={Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study},
+  author={Menglong Cui and Pengzhi Gao and Wei Liu and Jian Luan and Bin Wang},
+  year={2025},
+  eprint={2502.02481},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL},
+  url={https://arxiv.org/abs/2502.02481},
+}
+```
+
+For these quantized versions, please also credit:
+- **Quantization by**: [Tonic](https://huggingface.co/Tonic)
+- **Repository**: [Tonic/GemmaX2-28-2B-gguf](https://huggingface.co/Tonic/GemmaX2-28-2B-gguf)
+
+## Contact
+
+For questions about the original model, refer to Xiaomi’s publication. For issues with the GGUF quantizations, contact Tonic via Hugging Face discussions at `Tonic/GemmaX2-28-2B-gguf`.

evaluate.json

@@ -0,0 +1,107 @@
+{
+    "rouge": {
+        "rouge1": 0.6255101764812026,
+        "rouge2": 0.4212945982663935,
+        "rougeL": 0.5973657536570702,
+        "rougeLsum": 0.5985905113024548
+    },
+    "bleu": {
+        "bleu": 0.31871536850070264,
+        "precisions": [
+            0.6347305389221557,
+            0.39490445859872614,
+            0.2789115646258503,
+            0.19708029197080293
+        ],
+        "brevity_penalty": 0.9302618655343314,
+        "length_ratio": 0.9325842696629213,
+        "translation_length": 166.0,
+        "reference_length": 178.0
+    },
+    "metadata": {
+        "model": "hf.co/Tonic/GemmaX2-28-2B-gguf:BF16",
+        "run_id": "1740853522",
+        "timestamp": 1740853573.095875,
+        "datetime": "2025-03-01T13:26:13.095875",
+        "source_language": "English",
+        "source_code": "en",
+        "target_language": "Spanish",
+        "target_code": "es",
+        "source_texts": [
+            "It allows me to work by following my vibes and molding my teaching style to the learning style of the audience.",
+            "The unrelenting soul-force of those who would hold us accountable blows that all away.",
+            "When taken regularly in therapeutic doses, ginger root can effectively cure nausea;",
+            "They accomplished their goals and created a legacy of self-determination to which others may aspire.",
+            "But faster economic activity could also translate into some degree of inflation.",
+            "The main characteristics a stone should possess are uniform surface, grain, and density.",
+            "Lettuce, no matter the variety, is considered a cool-weather crop.",
+            "It was a trick to lure foolish humans to an ogre who would teach them a very valuable lesson.",
+            "Just to clarify, though, assertive is not the same as aggressive or arrogant.",
+            "The bus, normally crowded, was stunningly nearly empty at this hour."
+        ],
+        "prompts": [
+            "Translate this from English to Spanish:\nEnglish: It allows me to work by following my vibes and molding my teaching style to the learning style of the audience.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: The unrelenting soul-force of those who would hold us accountable blows that all away.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: When taken regularly in therapeutic doses, ginger root can effectively cure nausea;\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: They accomplished their goals and created a legacy of self-determination to which others may aspire.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: But faster economic activity could also translate into some degree of inflation.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: The main characteristics a stone should possess are uniform surface, grain, and density.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: Lettuce, no matter the variety, is considered a cool-weather crop.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: It was a trick to lure foolish humans to an ogre who would teach them a very valuable lesson.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: Just to clarify, though, assertive is not the same as aggressive or arrogant.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: The bus, normally crowded, was stunningly nearly empty at this hour.\nSpanish:"
+        ],
+        "references": [
+            [
+                "Me permite trabajar seg\u00fan mis impresiones y ajustar mis m\u00e9todos de ense\u00f1anza al modelo de aprendizaje del p\u00fablico."
+            ],
+            [
+                "La implacable fuerza del alma de quienes nos piden cuentas echa por tierra todo eso."
+            ],
+            [
+                "Si se toma de forma regular en dosis terap\u00e9uticas, la ra\u00edz de jengibre puede ser un remedio efectivo contra las n\u00e1useas;"
+            ],
+            [
+                "Han cumplido sus objetivos y creado un precedente de autodeterminaci\u00f3n al que otros es posible que aspiren."
+            ],
+            [
+                "Sin embargo, la r\u00e1pida actividad econ\u00f3mica tambi\u00e9n podr\u00eda conllevar un cierto grado de inflaci\u00f3n."
+            ],
+            [
+                "Las principales caracter\u00edsticas que deber\u00eda poseer una piedra son una superficie, un granulado y una densidad uniformes."
+            ],
+            [
+                "La lechuga, independientemente de la variedad, se considera un cultivo de clima fr\u00edo."
+            ],
+            [
+                "Fue una estrategia para llevar a ingenuos humanos hasta un ogro que les ense\u00f1ar\u00eda una muy valiosa lecci\u00f3n."
+            ],
+            [
+                "Aunque, como mera aclaraci\u00f3n, asertivo no es lo mismo que agresivo o arrogante."
+            ],
+            [
+                "El autob\u00fas, normalmente lleno de gente, estaba sorprendentemente casi vac\u00edo a esta hora."
+            ]
+        ],
+        "predictions": [
+            "Esto me permite trabajar siguiendo mis instintos y modelar mi estilo de ense\u00f1anza en funci\u00f3n del estilo de aprendizaje del p\u00fablico.",
+            "La implacable fuerza de los que nos responsabilizar\u00edan dispersa todo eso.",
+            "Si se toma regularmente en dosis terap\u00e9uticas, la ra\u00edz de jengibre puede curar eficazmente las n\u00e1useas.",
+            "Lograron sus objetivos y dejaron un legado de autodeterminaci\u00f3n al que otros pueden aspirar.",
+            "Pero una mayor actividad econ\u00f3mica podr\u00eda traducirse tambi\u00e9n en un cierto grado de inflaci\u00f3n.",
+            "Las principales caracter\u00edsticas que deber\u00eda tener una piedra son su superficie, grano y densidad uniformes.",
+            "La lechuga, independientemente de la variedad, se considera un cultivo para climas fr\u00edos.",
+            "Era un truco para atrapar a unos humanos tontos con el fin de ense\u00f1\u00e1rseles una valiosa lecci\u00f3n.",
+            "Pero, a fin de dejarlo claro, el concepto no es lo mismo que la agresividad o el orgullo.",
+            "El autob\u00fas estaba incre\u00edblemente vac\u00edo en esta hora normalmente tan concurrida."
+        ],
+        "samples": 10
+    },
+    "telemetry": {
+        "runtime": 47.645625591278076,
+        "avg_eval_time": 0.07864224910736084,
+        "avg_pred_time": 4.541392850875854,
+        "eval_rate": 2.518594278295445,
+        "pred_rate": 13.211805710318231
+    }
+}

gemmax2-28-2b-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47a0ecab1c83e5a8519ad97268251901e08c3f02a97743f62727f0eca471c39
+size 5235213664

gemmax2-28-2b-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae5b246b208abb034765050d3ac160fd187bb943d30e12b2af352960237c3f2
+size 5235213664

gemmax2-28-2b-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83f6f4fdac4edf9e0c954e0c516df965f4e5cf35a3c77d027be4e8673e5e7a5
+size 2784494944

gemmax2-28-2b-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44fa403aec99706e4ac9a6e40f21afae1a4fb8827069756048754d59eeeddda6
+size 1613657440

gemmax2-28-2b-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65c10a0155a846794acfb57d2d81747963fd10006f7405a7fb710e1aabae3c8
+size 1708545376

results_en_es_1740935448.json

@@ -0,0 +1,107 @@
+{
+    "rouge": {
+        "rouge1": 0.6230424412060338,
+        "rouge2": 0.41322763891410624,
+        "rougeL": 0.5914651417057188,
+        "rougeLsum": 0.5937938122982229
+    },
+    "bleu": {
+        "bleu": 0.3150735589106241,
+        "precisions": [
+            0.6358381502890174,
+            0.3803680981595092,
+            0.2679738562091503,
+            0.17482517482517482
+        ],
+        "brevity_penalty": 0.9657177024852738,
+        "length_ratio": 0.9662921348314607,
+        "translation_length": 172.0,
+        "reference_length": 178.0
+    },
+    "metadata": {
+        "model": "hf.co/Tonic/GemmaX2-28-2B-gguf:BF16",
+        "run_id": "1740935448",
+        "timestamp": 1740935505.1009474,
+        "datetime": "2025-03-02T18:11:45.100947",
+        "source_language": "English",
+        "source_code": "en",
+        "target_language": "Spanish",
+        "target_code": "es",
+        "source_texts": [
+            "It allows me to work by following my vibes and molding my teaching style to the learning style of the audience.",
+            "The unrelenting soul-force of those who would hold us accountable blows that all away.",
+            "When taken regularly in therapeutic doses, ginger root can effectively cure nausea;",
+            "They accomplished their goals and created a legacy of self-determination to which others may aspire.",
+            "But faster economic activity could also translate into some degree of inflation.",
+            "The main characteristics a stone should possess are uniform surface, grain, and density.",
+            "Lettuce, no matter the variety, is considered a cool-weather crop.",
+            "It was a trick to lure foolish humans to an ogre who would teach them a very valuable lesson.",
+            "Just to clarify, though, assertive is not the same as aggressive or arrogant.",
+            "The bus, normally crowded, was stunningly nearly empty at this hour."
+        ],
+        "prompts": [
+            "Translate this from English to Spanish:\nEnglish: It allows me to work by following my vibes and molding my teaching style to the learning style of the audience.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: The unrelenting soul-force of those who would hold us accountable blows that all away.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: When taken regularly in therapeutic doses, ginger root can effectively cure nausea;\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: They accomplished their goals and created a legacy of self-determination to which others may aspire.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: But faster economic activity could also translate into some degree of inflation.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: The main characteristics a stone should possess are uniform surface, grain, and density.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: Lettuce, no matter the variety, is considered a cool-weather crop.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: It was a trick to lure foolish humans to an ogre who would teach them a very valuable lesson.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: Just to clarify, though, assertive is not the same as aggressive or arrogant.\nSpanish:",
+            "Translate this from English to Spanish:\nEnglish: The bus, normally crowded, was stunningly nearly empty at this hour.\nSpanish:"
+        ],
+        "references": [
+            [
+                "Me permite trabajar seg\u00fan mis impresiones y ajustar mis m\u00e9todos de ense\u00f1anza al modelo de aprendizaje del p\u00fablico."
+            ],
+            [
+                "La implacable fuerza del alma de quienes nos piden cuentas echa por tierra todo eso."
+            ],
+            [
+                "Si se toma de forma regular en dosis terap\u00e9uticas, la ra\u00edz de jengibre puede ser un remedio efectivo contra las n\u00e1useas;"
+            ],
+            [
+                "Han cumplido sus objetivos y creado un precedente de autodeterminaci\u00f3n al que otros es posible que aspiren."
+            ],
+            [
+                "Sin embargo, la r\u00e1pida actividad econ\u00f3mica tambi\u00e9n podr\u00eda conllevar un cierto grado de inflaci\u00f3n."
+            ],
+            [
+                "Las principales caracter\u00edsticas que deber\u00eda poseer una piedra son una superficie, un granulado y una densidad uniformes."
+            ],
+            [
+                "La lechuga, independientemente de la variedad, se considera un cultivo de clima fr\u00edo."
+            ],
+            [
+                "Fue una estrategia para llevar a ingenuos humanos hasta un ogro que les ense\u00f1ar\u00eda una muy valiosa lecci\u00f3n."
+            ],
+            [
+                "Aunque, como mera aclaraci\u00f3n, asertivo no es lo mismo que agresivo o arrogante."
+            ],
+            [
+                "El autob\u00fas, normalmente lleno de gente, estaba sorprendentemente casi vac\u00edo a esta hora."
+            ]
+        ],
+        "predictions": [
+            "Me permite trabajar siguiendo mis propias vibraciones y adaptar mi estilo de ense\u00f1anza al estilo de aprendizaje del p\u00fablico asistente.",
+            "El implacable poder de aquellos que nos quieren hacer responsables nos derriba a todos.",
+            "Si se toma regularmente en dosis terap\u00e9uticas, la ra\u00edz de jengibre puede curar eficazmente el mareo.",
+            "Lograron sus objetivos y dejaron un legado de autodeterminaci\u00f3n al que otros pueden aspirar.",
+            "Pero la mayor actividad econ\u00f3mica podr\u00eda traducirse tambi\u00e9n en un cierto grado de inflaci\u00f3n.",
+            "Las principales caracter\u00edsticas que debe tener una piedra son la superficie, el grano y la densidad uniformes.",
+            "La lechuga, independientemente de su variedad, se considera un cultivo para climas fr\u00edos.",
+            "Fue un truco para atraer a los humanos tontos hacia un ogro que les ense\u00f1ar\u00eda una lecci\u00f3n muy valiosa.",
+            "Sin embargo, aclarado esto, tener asertividad no es lo mismo que ser agresivo o arrogante.",
+            "El autob\u00fas estaba incre\u00edblemente vac\u00edo en esta hora de la ma\u00f1ana normalmente tan concurrida."
+        ],
+        "samples": 10
+    },
+    "telemetry": {
+        "runtime": 15.239701747894287,
+        "avg_eval_time": 15.239701747894287,
+        "avg_pred_time": 1.1688670873641969,
+        "eval_rate": 3.937084924138385,
+        "pred_rate": 51.3317558930506
+    }
+}