Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,108 @@
+---
+language:
+- en
+- ro
+tags:
+- translation
+license: cc-by-4.0
+datasets:
+- quickmt/quickmt-train.ro-en
+model-index:
+- name: quickmt-ro-en
+  results:
+  - task:
+      name: Translation ron-eng
+      type: translation
+      args: ron-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: ron_Latn eng_Latn devtest
+    metrics:
+    - name: BLEU
+      type: bleu
+      value: 
+    - name: CHRF
+      type: chrf
+      value: 
+    - name: COMET
+      type: comet
+      value: 
+---
+
+
+# `quickmt-ro-en` Neural Machine Translation Model 
+
+`quickmt-ro-en` is a reasonably fast and reasonably accurate neural machine translation model for translation from `ro` into `en`.
+
+
+## Try it on our Huggingface Space
+
+Give it a try before downloading here: https://huggingface.co/spaces/quickmt/QuickMT-Demo
+
+
+## Model Information
+
+* Trained using [`eole`](https://github.com/eole-nlp/eole) 
+* 200M parameter transformer 'big' with 8 encoder layers and 2 decoder layers
+* 32k separate Sentencepiece vocabs
+* Expested for fast inference to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format
+* Training data: https://huggingface.co/datasets/quickmt/quickmt-train.lv-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-ro-en ./quickmt-ro-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-ro-en/", device="auto")
+
+# Translate - set beam size to 1 for faster speed (but lower quality)
+sample_text = 'Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia and chair of the clinical and scientific division of the Canadian Diabetes Association cautioned that the research is still in its early days.'
+
+t(sample_text, beam_size=5)
+```
+
+> 'Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia, and chairman of the clinical and scientific division of the Canadian Diabetic Association, pointed out that the research is still in its early stages.'
+
+```python
+# 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)
+```
+
+> 'Dr. Ehud Ur, profesor de medicina la Universitatea Dalhousie din Halifax, Nova Scotia și președinte al departamentului clinic și științific al Asociației Canadiene pentru Diabet, a avertizat că cercetările au ajuns în primele zile.'
+
+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`. A model in safetensors format to be used with `eole` is also provided.
+
+
+## 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) ("ron_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 Nvidia RTX 4070s GPU with batch size 32.
+
+
+|                                   |   bleu |   chrf2 |   comet22 |   Time (s) |
+|:----------------------------------|-------:|--------:|----------:|-----------:|
+| quickmt/quickmt-en-ro             |  42.29 |   66.07 |     89.67 |       1.48 |
+| Helsinki-NLP/opus-mt-tc-big-en-ro |  40.84 |   65.24 |     87.67 |       3.58 |
+| facebook/nllb-200-distilled-600M  |  35.26 |   61.93 |     89.19 |      27.74 |
+| facebook/nllb-200-distilled-1.3B  |  37.15 |   63.54 |     90.26 |      48.63 |
+| facebook/m2m100_418M              |  32.88 |   59.31 |     84.69 |      22.19 |
+| facebook/m2m100_1.2B              |  39.35 |   64.16 |     89.25 |      44.61 |
+

.ipynb_checkpoints/eole-config-checkpoint.yaml

@@ -0,0 +1,96 @@
+## IO
+save_data: data
+overwrite: True
+seed: 1234
+report_every: 100
+valid_metrics: ["BLEU"]
+tensorboard: true
+tensorboard_log_dir: tensorboard
+
+### Vocab
+src_vocab: en.eole.vocab
+tgt_vocab: ro.eole.vocab
+src_vocab_size: 32000
+tgt_vocab_size: 32000
+vocab_size_multiple: 8
+share_vocab: false
+n_sample: 0
+
+data:
+    corpus_1:
+        path_src: hf://quickmt/quickmt-train.ro-en/en
+        path_tgt: hf://quickmt/quickmt-train.ro-en/ro
+        path_sco: hf://quickmt/quickmt-train.ro-en/sco
+    valid:
+        path_src: valid.en
+        path_tgt: valid.ro
+
+transforms: [sentencepiece, filtertoolong]
+transforms_configs:
+  sentencepiece:
+    src_subword_model: "en.spm.model"
+    tgt_subword_model: "ro.spm.model"
+  filtertoolong:
+    src_seq_length: 256
+    tgt_seq_length: 256
+
+training:
+    # Run configuration
+    model_path: quickmt-en-ro-eole-model
+    #train_from: model
+    keep_checkpoint: 4
+    train_steps: 60000
+    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: 6000
+    valid_batch_size: 2048
+    batch_size_multiple: 8
+    accum_count: [20]
+    accum_steps: [0]
+
+    # Optimizer & Compute
+    compute_dtype: "fp16"
+    optim: "adamw"
+    #use_amp: False
+    learning_rate: 2.0
+    warmup_steps: 2000
+    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: true
+    hidden_size: 1024
+    encoder:
+        layers: 8
+    decoder:
+        layers: 2
+    heads: 8
+    transformer_ff: 4096
+    embeddings:
+        word_vec_size: 1024
+        position_encoding_type: "SinusoidalInterleaved"
+

README.md

@@ -1,3 +1,108 @@
----
-license: cc-by-4.0
----
+---
+language:
+- en
+- ro
+tags:
+- translation
+license: cc-by-4.0
+datasets:
+- quickmt/quickmt-train.ro-en
+model-index:
+- name: quickmt-ro-en
+  results:
+  - task:
+      name: Translation ron-eng
+      type: translation
+      args: ron-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: ron_Latn eng_Latn devtest
+    metrics:
+    - name: BLEU
+      type: bleu
+      value: 
+    - name: CHRF
+      type: chrf
+      value: 
+    - name: COMET
+      type: comet
+      value: 
+---
+
+
+# `quickmt-ro-en` Neural Machine Translation Model 
+
+`quickmt-ro-en` is a reasonably fast and reasonably accurate neural machine translation model for translation from `ro` into `en`.
+
+
+## Try it on our Huggingface Space
+
+Give it a try before downloading here: https://huggingface.co/spaces/quickmt/QuickMT-Demo
+
+
+## Model Information
+
+* Trained using [`eole`](https://github.com/eole-nlp/eole) 
+* 200M parameter transformer 'big' with 8 encoder layers and 2 decoder layers
+* 32k separate Sentencepiece vocabs
+* Expested for fast inference to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format
+* Training data: https://huggingface.co/datasets/quickmt/quickmt-train.lv-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-ro-en ./quickmt-ro-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-ro-en/", device="auto")
+
+# Translate - set beam size to 1 for faster speed (but lower quality)
+sample_text = 'Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia and chair of the clinical and scientific division of the Canadian Diabetes Association cautioned that the research is still in its early days.'
+
+t(sample_text, beam_size=5)
+```
+
+> 'Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia, and chairman of the clinical and scientific division of the Canadian Diabetic Association, pointed out that the research is still in its early stages.'
+
+```python
+# 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)
+```
+
+> 'Dr. Ehud Ur, profesor de medicina la Universitatea Dalhousie din Halifax, Nova Scotia și președinte al departamentului clinic și științific al Asociației Canadiene pentru Diabet, a avertizat că cercetările au ajuns în primele zile.'
+
+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`. A model in safetensors format to be used with `eole` is also provided.
+
+
+## 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) ("ron_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 Nvidia RTX 4070s GPU with batch size 32.
+
+
+|                                   |   bleu |   chrf2 |   comet22 |   Time (s) |
+|:----------------------------------|-------:|--------:|----------:|-----------:|
+| quickmt/quickmt-en-ro             |  42.29 |   66.07 |     89.67 |       1.48 |
+| Helsinki-NLP/opus-mt-tc-big-en-ro |  40.84 |   65.24 |     87.67 |       3.58 |
+| facebook/nllb-200-distilled-600M  |  35.26 |   61.93 |     89.19 |      27.74 |
+| facebook/nllb-200-distilled-1.3B  |  37.15 |   63.54 |     90.26 |      48.63 |
+| facebook/m2m100_418M              |  32.88 |   59.31 |     84.69 |      22.19 |
+| facebook/m2m100_1.2B              |  39.35 |   64.16 |     89.25 |      44.61 |
+

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 +1,96 @@
+## IO
+save_data: data
+overwrite: True
+seed: 1234
+report_every: 100
+valid_metrics: ["BLEU"]
+tensorboard: true
+tensorboard_log_dir: tensorboard
+
+### Vocab
+src_vocab: en.eole.vocab
+tgt_vocab: ro.eole.vocab
+src_vocab_size: 32000
+tgt_vocab_size: 32000
+vocab_size_multiple: 8
+share_vocab: false
+n_sample: 0
+
+data:
+    corpus_1:
+        path_src: hf://quickmt/quickmt-train.ro-en/en
+        path_tgt: hf://quickmt/quickmt-train.ro-en/ro
+        path_sco: hf://quickmt/quickmt-train.ro-en/sco
+    valid:
+        path_src: valid.en
+        path_tgt: valid.ro
+
+transforms: [sentencepiece, filtertoolong]
+transforms_configs:
+  sentencepiece:
+    src_subword_model: "en.spm.model"
+    tgt_subword_model: "ro.spm.model"
+  filtertoolong:
+    src_seq_length: 256
+    tgt_seq_length: 256
+
+training:
+    # Run configuration
+    model_path: quickmt-en-ro-eole-model
+    #train_from: model
+    keep_checkpoint: 4
+    train_steps: 60000
+    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: 6000
+    valid_batch_size: 2048
+    batch_size_multiple: 8
+    accum_count: [20]
+    accum_steps: [0]
+
+    # Optimizer & Compute
+    compute_dtype: "fp16"
+    optim: "adamw"
+    #use_amp: False
+    learning_rate: 2.0
+    warmup_steps: 2000
+    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: true
+    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 @@
+{
+  "tensorboard_log_dir_dated": "tensorboard/Oct-12_21-42-37",
+  "share_vocab": false,
+  "tgt_vocab_size": 32000,
+  "valid_metrics": [
+    "BLEU"
+  ],
+  "n_sample": 0,
+  "seed": 1234,
+  "vocab_size_multiple": 8,
+  "overwrite": true,
+  "tgt_vocab": "ro.eole.vocab",
+  "src_vocab_size": 32000,
+  "src_vocab": "en.eole.vocab",
+  "save_data": "data",
+  "report_every": 100,
+  "transforms": [
+    "sentencepiece",
+    "filtertoolong"
+  ],
+  "tensorboard_log_dir": "tensorboard",
+  "tensorboard": true,
+  "training": {
+    "keep_checkpoint": 4,
+    "optim": "adamw",
+    "label_smoothing": 0.1,
+    "average_decay": 0.0001,
+    "learning_rate": 2.0,
+    "save_checkpoint_steps": 5000,
+    "bucket_size": 128000,
+    "max_grad_norm": 0.0,
+    "dropout": [
+      0.1
+    ],
+    "train_steps": 100000,
+    "batch_type": "tokens",
+    "num_workers": 0,
+    "prefetch_factor": 32,
+    "normalization": "tokens",
+    "gpu_ranks": [
+      0
+    ],
+    "compute_dtype": "torch.float16",
+    "model_path": "quickmt-en-ro-eole-model",
+    "world_size": 1,
+    "adam_beta2": 0.998,
+    "dropout_steps": [
+      0
+    ],
+    "valid_batch_size": 2048,
+    "attention_dropout": [
+      0.1
+    ],
+    "decay_method": "noam",
+    "param_init_method": "xavier_uniform",
+    "batch_size_multiple": 8,
+    "warmup_steps": 2000,
+    "accum_steps": [
+      0
+    ],
+    "valid_steps": 5000,
+    "accum_count": [
+      20
+    ],
+    "batch_size": 6000
+  },
+  "model": {
+    "position_encoding_type": "SinusoidalInterleaved",
+    "share_decoder_embeddings": true,
+    "share_embeddings": false,
+    "transformer_ff": 4096,
+    "heads": 8,
+    "hidden_size": 1024,
+    "architecture": "transformer",
+    "embeddings": {
+      "tgt_word_vec_size": 1024,
+      "position_encoding_type": "SinusoidalInterleaved",
+      "word_vec_size": 1024,
+      "src_word_vec_size": 1024
+    },
+    "encoder": {
+      "encoder_type": "transformer",
+      "position_encoding_type": "SinusoidalInterleaved",
+      "n_positions": null,
+      "transformer_ff": 4096,
+      "heads": 8,
+      "hidden_size": 1024,
+      "src_word_vec_size": 1024,
+      "layers": 8
+    },
+    "decoder": {
+      "position_encoding_type": "SinusoidalInterleaved",
+      "n_positions": null,
+      "transformer_ff": 4096,
+      "heads": 8,
+      "hidden_size": 1024,
+      "decoder_type": "transformer",
+      "layers": 2,
+      "tgt_word_vec_size": 1024
+    }
+  },
+  "transforms_configs": {
+    "sentencepiece": {
+      "src_subword_model": "${MODEL_PATH}/en.spm.model",
+      "tgt_subword_model": "${MODEL_PATH}/ro.spm.model"
+    },
+    "filtertoolong": {
+      "src_seq_length": 256,
+      "tgt_seq_length": 256
+    }
+  },
+  "data": {
+    "corpus_1": {
+      "path_align": null,
+      "path_tgt": "train.ro",
+      "transforms": [
+        "sentencepiece",
+        "filtertoolong"
+      ],
+      "path_src": "train.en"
+    },
+    "valid": {
+      "path_align": null,
+      "path_tgt": "valid.ro",
+      "transforms": [
+        "sentencepiece",
+        "filtertoolong"
+      ],
+      "path_src": "valid.en"
+    }
+  }
+}

eole-model/en.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0b667cb624705e59a1af53a05118ead90fd9ddb695880b7a9000601b445276
+size 804879

eole-model/model.00.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336405c80c29b558313d412153967b3c08b077be9d9bc36ff8bcf453ed2a4053
+size 840314816

eole-model/ro.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cbacefea2837d7161439e3476c8ad05ad11826be8f3563db1bcb6748f373cb7
+size 829294

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d033740ae19bcaab6aeed907554bfc4a80dc112caae1fe6db23804876e8280
+size 409915789

src.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db0b667cb624705e59a1af53a05118ead90fd9ddb695880b7a9000601b445276
+size 804879

tgt.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cbacefea2837d7161439e3476c8ad05ad11826be8f3563db1bcb6748f373cb7
+size 829294