Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,101 @@
+---
+language:
+- en
+- it
+tags:
+- translation
+license: cc-by-4.0
+datasets:
+- quickmt/quickmt-train.it-en
+model-index:
+- name: quickmt-it-en
+  results:
+  - task:
+      name: Translation ita-eng
+      type: translation
+      args: ita-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: ita_Latn eng_Latn devtest
+    metrics:
+    - name: CHRF
+      type: chrf
+      value: 61.48 
+    - name: BLEU
+      type: bleu
+      value: 32.10
+    - name: COMET
+      type: comet
+      value: 87.31
+---
+
+
+# `quickmt-it-en` Neural Machine Translation Model 
+
+`quickmt-it-en` is a reasonably fast and reasonably accurate neural machine translation model for translation from `it` into `en`.
+
+
+## Model Information
+
+* Trained using [`eole`](https://github.com/eole-nlp/eole)
+* 185M parameter transformer 'big' with 8 encoder layers and 2 decoder layers
+* 50k joint Sentencepiece vocabulary
+* Exported for fast inference to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format
+* Training data: https://huggingface.co/datasets/quickmt/quickmt-train.it-en/tree/main
+
+See the `eole` model configuration in this repository for further details and the `eole-model` for the raw `eole` (pytorch) model.
+
+## Usage with `quickmt`
+
+You must install the Nvidia cuda toolkit first, if you want to do GPU inference.
+
+Next, install the `quickmt` python library and download the model:
+
+```bash
+git clone https://github.com/quickmt/quickmt.git
+pip install ./quickmt/
+
+quickmt-model-download quickmt/quickmt-it-en ./quickmt-it-en
+```
+
+Finally use the model in python:
+
+```python
+from quickmt import Translator
+
+# Auto-detects GPU, set to "cpu" to force CPU inference
+t = Translator("./quickmt-it-en/", device="auto")
+
+# Translate - set beam size to 1 for faster speed (but lower quality)
+sample_text = "Lo studio è ancora in fase iniziale, come dichiarato cautelativamente dal dottor Ehud Ur, professore di medicina alla Dalhousie University di Halifax, Nuova Scozia, e direttore del dipartimento clinico e scientifico della Canadian Diabetes Association."
+t(sample_text, beam_size=5)
+
+> 'The study is still in its early stages, as cautiously stated by Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia, and director of the clinical and scientific department of the Canadian Diabetes Association.'
+
+# Get alternative translations by sampling
+# You can pass any cTranslate2 `translate_batch` arguments
+t([sample_text], sampling_temperature=1.2, beam_size=1, sampling_topk=50, sampling_topp=0.9)
+
+> 'The study is still in the early stages, as indicated cautiously by Dr. Ehud Ur, Medical professor at Dalhousie University of Halifax, Nova Scotia, and director of clinical and scientific department at the Canadian Diabetes Association.'
+```
+
+The model is in `ctranslate2` format, and the tokenizers are `sentencepiece`, so you can use `ctranslate2` directly instead of through `quickmt`. It is also possible  to get this model to work with e.g. [LibreTranslate](https://libretranslate.com/) which also uses `ctranslate2` and `sentencepiece`.
+
+
+## Metrics
+
+`bleu` and `chrf2` are calculated with [sacrebleu](https://github.com/mjpost/sacrebleu) on the [Flores200 `devtest` test set](https://huggingface.co/datasets/facebook/flores) ("ita_Latn"->"eng_Latn"). `comet22` with the [`comet`](https://github.com/Unbabel/COMET) library and the [default model](https://huggingface.co/Unbabel/wmt22-comet-da). "Time (s)" is the time in seconds to translate the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32 (faster speed is possible using a larger batch size).
+
+## it -> en flores-devtest metrics
+
+|                                  |   bleu |   chrf2 |   comet22 |   Time (s) |
+|:---------------------------------|-------:|--------:|----------:|-----------:|
+| quickmt/quickmt-it-en            |  32.1  |   61.48 |     87.31 |       1.04 |
+| Helsink-NLP/opus-mt-it-en        |  29.48 |   59.96 |     86.59 |       4.39 |
+| facebook/nllb-200-distilled-600M |  33.49 |   61.97 |     87.39 |      22.16 |
+| facebook/nllb-200-distilled-1.3B |  34.97 |   63.23 |     88.14 |      38.26 |
+| facebook/m2m100_418M             |  25.92 |   56.94 |     83.14 |      18.61 |
+| facebook/m2m100_1.2B             |  30.81 |   60.43 |     86.43 |      36.28 |
+
+`quickmt-it-en` is the fastest and is higher quality than `opus-mt-it-en`, `m2m100_418m` and `m2m100_1.2B`. 

README.md

@@ -1,3 +1,101 @@
----
-license: cc-by-4.0
----
+---
+language:
+- en
+- it
+tags:
+- translation
+license: cc-by-4.0
+datasets:
+- quickmt/quickmt-train.it-en
+model-index:
+- name: quickmt-it-en
+  results:
+  - task:
+      name: Translation ita-eng
+      type: translation
+      args: ita-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: ita_Latn eng_Latn devtest
+    metrics:
+    - name: CHRF
+      type: chrf
+      value: 61.48 
+    - name: BLEU
+      type: bleu
+      value: 32.10
+    - name: COMET
+      type: comet
+      value: 87.31
+---
+
+
+# `quickmt-it-en` Neural Machine Translation Model 
+
+`quickmt-it-en` is a reasonably fast and reasonably accurate neural machine translation model for translation from `it` into `en`.
+
+
+## Model Information
+
+* Trained using [`eole`](https://github.com/eole-nlp/eole)
+* 185M parameter transformer 'big' with 8 encoder layers and 2 decoder layers
+* 50k joint Sentencepiece vocabulary
+* Exported for fast inference to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format
+* Training data: https://huggingface.co/datasets/quickmt/quickmt-train.it-en/tree/main
+
+See the `eole` model configuration in this repository for further details and the `eole-model` for the raw `eole` (pytorch) model.
+
+## Usage with `quickmt`
+
+You must install the Nvidia cuda toolkit first, if you want to do GPU inference.
+
+Next, install the `quickmt` python library and download the model:
+
+```bash
+git clone https://github.com/quickmt/quickmt.git
+pip install ./quickmt/
+
+quickmt-model-download quickmt/quickmt-it-en ./quickmt-it-en
+```
+
+Finally use the model in python:
+
+```python
+from quickmt import Translator
+
+# Auto-detects GPU, set to "cpu" to force CPU inference
+t = Translator("./quickmt-it-en/", device="auto")
+
+# Translate - set beam size to 1 for faster speed (but lower quality)
+sample_text = "Lo studio è ancora in fase iniziale, come dichiarato cautelativamente dal dottor Ehud Ur, professore di medicina alla Dalhousie University di Halifax, Nuova Scozia, e direttore del dipartimento clinico e scientifico della Canadian Diabetes Association."
+t(sample_text, beam_size=5)
+
+> 'The study is still in its early stages, as cautiously stated by Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia, and director of the clinical and scientific department of the Canadian Diabetes Association.'
+
+# Get alternative translations by sampling
+# You can pass any cTranslate2 `translate_batch` arguments
+t([sample_text], sampling_temperature=1.2, beam_size=1, sampling_topk=50, sampling_topp=0.9)
+
+> 'The study is still in the early stages, as indicated cautiously by Dr. Ehud Ur, Medical professor at Dalhousie University of Halifax, Nova Scotia, and director of clinical and scientific department at the Canadian Diabetes Association.'
+```
+
+The model is in `ctranslate2` format, and the tokenizers are `sentencepiece`, so you can use `ctranslate2` directly instead of through `quickmt`. It is also possible  to get this model to work with e.g. [LibreTranslate](https://libretranslate.com/) which also uses `ctranslate2` and `sentencepiece`.
+
+
+## Metrics
+
+`bleu` and `chrf2` are calculated with [sacrebleu](https://github.com/mjpost/sacrebleu) on the [Flores200 `devtest` test set](https://huggingface.co/datasets/facebook/flores) ("ita_Latn"->"eng_Latn"). `comet22` with the [`comet`](https://github.com/Unbabel/COMET) library and the [default model](https://huggingface.co/Unbabel/wmt22-comet-da). "Time (s)" is the time in seconds to translate the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32 (faster speed is possible using a larger batch size).
+
+## it -> en flores-devtest metrics
+
+|                                  |   bleu |   chrf2 |   comet22 |   Time (s) |
+|:---------------------------------|-------:|--------:|----------:|-----------:|
+| quickmt/quickmt-it-en            |  32.1  |   61.48 |     87.31 |       1.04 |
+| Helsink-NLP/opus-mt-it-en        |  29.48 |   59.96 |     86.59 |       4.39 |
+| facebook/nllb-200-distilled-600M |  33.49 |   61.97 |     87.39 |      22.16 |
+| facebook/nllb-200-distilled-1.3B |  34.97 |   63.23 |     88.14 |      38.26 |
+| facebook/m2m100_418M             |  25.92 |   56.94 |     83.14 |      18.61 |
+| facebook/m2m100_1.2B             |  30.81 |   60.43 |     86.43 |      36.28 |
+
+`quickmt-it-en` is the fastest and is higher quality than `opus-mt-it-en`, `m2m100_418m` and `m2m100_1.2B`. 

config.json

@@ -0,0 +1,10 @@
+{
+  "add_source_bos": false,
+  "add_source_eos": false,
+  "bos_token": "<s>",
+  "decoder_start_token": "<s>",
+  "eos_token": "</s>",
+  "layer_norm_epsilon": 1e-06,
+  "multi_query_attention": false,
+  "unk_token": "<unk>"
+}

eole-config.yaml

@@ -0,0 +1,98 @@
+## IO
+save_data: data
+overwrite: True
+seed: 1234
+report_every: 100
+valid_metrics: ["BLEU"]
+tensorboard: true
+tensorboard_log_dir: tensorboard
+
+### Vocab
+src_vocab: it.eole.vocab
+tgt_vocab: en.eole.vocab
+src_vocab_size: 20000
+tgt_vocab_size: 20000
+vocab_size_multiple: 8
+share_vocab: false
+n_sample: 0
+
+data:
+    corpus_1:
+        # path_src: hf://quickmt/quickmt-train.ja-en/ja
+        # path_tgt: hf://quickmt/quickmt-train.ja-en/en
+        # path_sco: hf://quickmt/quickmt-train.ja-en/sco
+        path_src: train.it
+        path_tgt: train.en
+    valid:
+        path_src: valid.it
+        path_tgt: valid.en
+
+transforms: [sentencepiece, filtertoolong]
+transforms_configs:
+  sentencepiece:
+    src_subword_model: "it.spm.model"
+    tgt_subword_model: "en.spm.model"
+  filtertoolong:
+    src_seq_length: 256
+    tgt_seq_length: 256
+
+training:
+    # Run configuration
+    model_path: quickmt-it-en-eole-model
+    #train_from: model
+    keep_checkpoint: 4
+    train_steps: 100000
+    save_checkpoint_steps: 5000
+    valid_steps: 5000
+    
+    # Train on a single GPU
+    world_size: 1
+    gpu_ranks: [0]
+
+    # Batching 10240
+    batch_type: "tokens"
+    batch_size: 8000
+    valid_batch_size: 4096
+    batch_size_multiple: 8
+    accum_count: [10]
+    accum_steps: [0]
+
+    # Optimizer & Compute
+    compute_dtype: "fp16"
+    optim: "adamw"
+    #use_amp: False
+    learning_rate: 2.0
+    warmup_steps: 4000
+    decay_method: "noam"
+    adam_beta2: 0.998
+
+    # Data loading
+    bucket_size: 128000
+    num_workers: 4
+    prefetch_factor: 32
+    
+    # Hyperparams
+    dropout_steps: [0]
+    dropout: [0.1]
+    attention_dropout: [0.1]
+    max_grad_norm: 0
+    label_smoothing: 0.1
+    average_decay: 0.0001
+    param_init_method: xavier_uniform
+    normalization: "tokens"
+
+model:
+    architecture: "transformer"
+    share_embeddings: false
+    share_decoder_embeddings: false
+    hidden_size: 1024
+    encoder:
+        layers: 8
+    decoder:
+        layers: 2
+    heads: 8
+    transformer_ff: 4096
+    embeddings:
+        word_vec_size: 1024
+        position_encoding_type: "SinusoidalInterleaved"
+

eole-model/config.json

@@ -0,0 +1,132 @@
+{
+  "valid_metrics": [
+    "BLEU"
+  ],
+  "transforms": [
+    "sentencepiece",
+    "filtertoolong"
+  ],
+  "tensorboard_log_dir": "tensorboard",
+  "n_sample": 0,
+  "report_every": 100,
+  "tensorboard": true,
+  "tgt_vocab_size": 20000,
+  "save_data": "data",
+  "src_vocab_size": 20000,
+  "src_vocab": "it.eole.vocab",
+  "vocab_size_multiple": 8,
+  "tgt_vocab": "en.eole.vocab",
+  "share_vocab": false,
+  "overwrite": true,
+  "seed": 1234,
+  "tensorboard_log_dir_dated": "tensorboard/Apr-19_20-07-23",
+  "training": {
+    "num_workers": 0,
+    "normalization": "tokens",
+    "learning_rate": 2.0,
+    "gpu_ranks": [
+      0
+    ],
+    "accum_count": [
+      10
+    ],
+    "accum_steps": [
+      0
+    ],
+    "valid_batch_size": 4096,
+    "valid_steps": 5000,
+    "world_size": 1,
+    "warmup_steps": 4000,
+    "prefetch_factor": 32,
+    "compute_dtype": "torch.float16",
+    "batch_size": 8000,
+    "decay_method": "noam",
+    "dropout": [
+      0.1
+    ],
+    "batch_type": "tokens",
+    "model_path": "quickmt-it-en-eole-model",
+    "keep_checkpoint": 4,
+    "save_checkpoint_steps": 5000,
+    "param_init_method": "xavier_uniform",
+    "attention_dropout": [
+      0.1
+    ],
+    "average_decay": 0.0001,
+    "batch_size_multiple": 8,
+    "dropout_steps": [
+      0
+    ],
+    "adam_beta2": 0.998,
+    "max_grad_norm": 0.0,
+    "optim": "adamw",
+    "train_steps": 100000,
+    "bucket_size": 128000,
+    "label_smoothing": 0.1
+  },
+  "transforms_configs": {
+    "filtertoolong": {
+      "src_seq_length": 256,
+      "tgt_seq_length": 256
+    },
+    "sentencepiece": {
+      "tgt_subword_model": "${MODEL_PATH}/en.spm.model",
+      "src_subword_model": "${MODEL_PATH}/it.spm.model"
+    }
+  },
+  "data": {
+    "corpus_1": {
+      "transforms": [
+        "sentencepiece",
+        "filtertoolong"
+      ],
+      "path_align": null,
+      "path_src": "train.it",
+      "path_tgt": "train.en"
+    },
+    "valid": {
+      "transforms": [
+        "sentencepiece",
+        "filtertoolong"
+      ],
+      "path_align": null,
+      "path_src": "valid.it",
+      "path_tgt": "valid.en"
+    }
+  },
+  "model": {
+    "share_decoder_embeddings": false,
+    "share_embeddings": false,
+    "architecture": "transformer",
+    "heads": 8,
+    "transformer_ff": 4096,
+    "hidden_size": 1024,
+    "position_encoding_type": "SinusoidalInterleaved",
+    "decoder": {
+      "n_positions": null,
+      "tgt_word_vec_size": 1024,
+      "decoder_type": "transformer",
+      "layers": 2,
+      "heads": 8,
+      "transformer_ff": 4096,
+      "hidden_size": 1024,
+      "position_encoding_type": "SinusoidalInterleaved"
+    },
+    "embeddings": {
+      "src_word_vec_size": 1024,
+      "tgt_word_vec_size": 1024,
+      "position_encoding_type": "SinusoidalInterleaved",
+      "word_vec_size": 1024
+    },
+    "encoder": {
+      "n_positions": null,
+      "layers": 8,
+      "encoder_type": "transformer",
+      "heads": 8,
+      "src_word_vec_size": 1024,
+      "transformer_ff": 4096,
+      "hidden_size": 1024,
+      "position_encoding_type": "SinusoidalInterleaved"
+    }
+  }
+}

eole-model/en.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352edbef8a5896ac750aa1318696d770c15c85d79116c94b4872086a1de94b2d
+size 586485

eole-model/it.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b20d73c2224922ffef2d6f4bbe72810d7f75c80281dcea17515fc25a7a7bb9
+size 598389

eole-model/model.00.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e195c32a95b45a6a76c85058eab4599344baaeb524adb1c3fb063177139c532b
+size 823882912

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21873987a0bbc65658e63823a4637b9e15b2a98030b84e9fb42a5c2566bfcd5c
+size 401699775

src.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47b20d73c2224922ffef2d6f4bbe72810d7f75c80281dcea17515fc25a7a7bb9
+size 598389

tgt.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352edbef8a5896ac750aa1318696d770c15c85d79116c94b4872086a1de94b2d
+size 586485