Translation
Transformers
ONNX
Safetensors
Khmer
blenderbot
text2text-generation
transliteration
romanization
romanized-khmer
khmer
character-level
int8
keyboard
on-device
Eval Results (legacy)
Instructions to use samdei/samdei-type-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use samdei/samdei-type-mini with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="samdei/samdei-type-mini")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("samdei/samdei-type-mini") model = AutoModelForSeq2SeqLM.from_pretrained("samdei/samdei-type-mini", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download rerank.json from samdei/samdei-type-mini: direct link, hf CLI and curl.
- Browser
- Download file 697 Bytes
-
https://huggingface.co/samdei/samdei-type-mini/resolve/main/rerank.json
- Command line
-
hf download hf://samdei/samdei-type-mini/rerank.json
-
curl -L -o rerank.json https://huggingface.co/samdei/samdei-type-mini/resolve/main/rerank.json
697 Bytes
| { | |
| "model": "Samdei Type Mini", | |
| "backend": "onnx", | |
| "beam": 5, | |
| "chunk_max_words": 8, | |
| "chunk_rule": "samdei_type.evaluation.chunk_source: at most 8 words per piece, break after any punctuation mark; pieces are decoded and reranked on their own and joined with a space", | |
| "rerank_weights": {"char": 0.0, "word": 0.3, "oov": 1.0, "channel": 0.0}, | |
| "score": "log P(y|x) + char*log P_char(y) + word*log P_word(y) - oov*#OOV(y) + channel*log P_ch(x|y)", | |
| "char_lm": null, | |
| "word_lm": "lm/wordfull_nowiki_p25.json.gz", | |
| "channel_model": null, | |
| "max_input_chars": 249, | |
| "weights_tuned_on": "closed development set, whole input, 2-fold cross-validated grid search; applied unchanged to 8-word pieces" | |
| } | |