Upload folder using huggingface_hub

README.md

@@ -0,0 +1,105 @@
+---
+language:
+- uk
+- en
+tags:
+- translation
+license: cc-by-4.0
+datasets:
+- quickmt/quickmt-train.uk-en
+- quickmt/finetranslations-sample-uk-en
+- HuggingFaceFW/finetranslations
+model-index:
+- name: quickmt-uk-en
+  results:
+  - task:
+      name: Translation ukr-eng
+      type: translation
+      args: ukr-eng
+    dataset:
+      name: flores101-devtest
+      type: flores_101
+      args: ukr_Cyrl eng_Latn devtest
+    metrics:
+    - name: BLEU
+      type: bleu
+      value: 39.88
+    - name: CHRF
+      type: chrf
+      value: 65.65
+
+---
+
+
+# `quickmt-uk-en` Neural Machine Translation Model 
+
+`quickmt-uk-en` is a reasonably fast and reasonably accurate neural machine translation model for translation from `uk` into `en`.
+
+`quickmt` models are roughly 3 times faster for GPU inference than OpusMT models and roughly [40 times](https://huggingface.co/spaces/quickmt/quickmt-vs-libretranslate) faster than [LibreTranslate](https://huggingface.co/spaces/quickmt/quickmt-vs-libretranslate)/[ArgosTranslate](github.com/argosopentech/argos-translate). 
+
+
+## Try it on our Huggingface Space
+
+Give it a try before downloading here: https://huggingface.co/spaces/quickmt/QuickMT-Demo
+
+
+## Model Information
+
+* Trained using [`quickmt-train`](github.com/quickmt/quickmt-train) 
+* 200M parameter seq2seq transformer
+* 32k separate Sentencepiece vocabs
+* Exported for fast inference to [CTranslate2](https://github.com/OpenNMT/CTranslate2) format
+* The pytorch model (for fine-tuning or pytorch inference) is available in this repository in the `pytorch_model` folder
+  * Config file here: `pytorch_model/config.yaml`
+
+
+## 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 -e ./quickmt/
+```
+
+Finally use the model in python:
+
+```python
+from quickmt import Translator
+
+# Auto-detects GPU, set to "cpu" to force CPU inference
+mt = Translator("quickmt/quickmt-uk-en", device="auto")
+
+# Translate - set beam size to 1 for faster speed (but lower quality)
+sample_text = 'Д-р Ехуд Ур, професор медицини в Університеті Делхаузі у Галіфаксі, Нова Шотландія, і голова клінічного та наукового відділу Канадської Асоціації Діабету, попередив, що дослідження лише починаються.'
+
+mt(sample_text, beam_size=5)
+```
+
+> 'Dr. Ehud Ur, a professor of medicine at Delhouse University in Halifax, Nova Scotia, and head of the clinical and scientific division of the Canadian Diabetes Association, warned that the research is just beginning.'
+
+```python
+# Get alternative translations by sampling
+# You can pass any cTranslate2 `translate_batch` arguments
+mt([sample_text], sampling_temperature=1.2, beam_size=1, sampling_topk=50, sampling_topp=0.9)
+```
+
+> 'Dr Ehud Uhr, an associate professor of medicine at Delhousy University in Halifax, Nova Scotia and the head of the clinical and scientific department of the Canadian Diabetes Association, has warned that the research has just started.'
+
+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).  "Time (s)" is the time in seconds to translate the flores-devtest dataset (1012 sentences) on an RTX 4070s GPU with batch size 32.
+
+
+| Model                              | time  | bleu  | chrf  |
+|------------------------------------|-------|-------|-------|
+| quickmt/quickmt_uk_en              | 1.12  | 39.88 | 65.65 |
+| Helsinki-NLP/opus-mt-tc-big-zle-en | 3.03  | 39.07 | 64.98 |
+| facebook/nllb-200-distilled-1.3B   | 17.25 | 33.59 | 63.50 |
+| CohereLabs/tiny-aya-global         | 23.36 | 37.60 | 63.73 |
+| google/gemma-4-E2B-it              | 47.71 | 37.22 | 63.75 |

config.json

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

model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63c061e3a0eed8b61527ded6a9e5f8a74364983c454ee4652cc995a1eb612be
+size 202004997

pytorch_model/averaged_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d59db4c8760263746c13387981f148c466b4712b0fbed7f31ef209db179c274
+size 799828424

pytorch_model/config.yaml

@@ -0,0 +1,51 @@
+model:
+  d_model: 768
+  enc_layers: 12
+  dec_layers: 2
+  n_heads: 16
+  ffn_dim: 4096
+  max_len: 256
+  vocab_size_src: 32000
+  vocab_size_tgt: 32000
+  dropout: 0.05
+  mlp_type: "standard" # standard or gated
+  activation: "gelu" # gelu or silu
+  norm_type: "layernorm" # layernorm or rmsnorm
+  ff_bias: true
+  tie_decoder_embeddings: false
+  layernorm_eps: 1.0e-5
+
+data:
+  src_lang: "uk"
+  tgt_lang: "en"
+  src_dev_path: "dev.ukr"
+  tgt_dev_path: "dev.eng"
+  max_tokens_per_batch: 6000
+  src_spm_nbest_size: -1
+  src_spm_alpha: 0.5
+  tgt_spm_nbest_size: 1
+  tgt_spm_alpha: 1.0
+  corpora:
+    - src_file: "train.cleaned.filtered.ukr"
+      tgt_file: "train.cleaned.filtered.eng"
+      weight: 1
+      start_step: 1000
+    - src_file: "finetranslations.ukr_Cyrl-eng_Latn.ukr_Cyrl"
+      tgt_file: "finetranslations.ukr_Cyrl-eng_Latn.eng_Latn"
+      weight: 1
+      start_step: 0
+      stop_step: 80000
+
+train:
+  experiment_name: "uken-base"
+  lr: 2.5e-3
+  grad_clip: 0.5
+  accum_steps: 20
+  max_checkpoints: 10
+  precision: "bfloat16"
+  warmup_steps: 5000
+  max_steps: 108000
+  eval_steps: 1000
+  
+export:
+  k: 5

pytorch_model/tokenizer_src.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ae41ace20c5b2b4287ac9d402cf93f6f857901b10ae1b20f22544073ce1c85
+size 1014232

pytorch_model/tokenizer_tgt.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832da24581d0516be8980cba35eab07fb575e703da700a919aac92d9c5c31311
+size 804561

src.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ae41ace20c5b2b4287ac9d402cf93f6f857901b10ae1b20f22544073ce1c85
+size 1014232

tgt.spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832da24581d0516be8980cba35eab07fb575e703da700a919aac92d9c5c31311
+size 804561