denishen0000/English-Amharic-Translation-project

# English-Amharic Merge Merged implementation combining encoder-decoder and decoder-only fine-tuning from `dai/english-amharic`, contrastive preference optimization (CPO) from `rahman/english-amharic`, and manual prefix tuning / manual OFT from `rijal/english-amharic`. ## Setup Copy `local_env.sh.example` to `local_env.sh` and set paths for your environment. Install dependencies from your existing environment (transformers, peft, torch, evaluate, etc.). Update corpus paths in your config JSON before running. ## Training entry points | Experiment type | Script | Config flags | |-----------------|--------|--------------| | Encoder-decoder SFT / LoRA / full FT | `finetune.py` | Standard `bitexts` with `src`/`tgt` | | CPO (contrastive preference optimization) | `finetune_cpo.py` | `cpo: true`, bitext with `src`/`good`/`bad` | | Manual prefix / OFT / stacked adapters | `finetune.py` | `use_prefix_tuning`, `use_oft`, `use_lora` | | Decoder-only SFT | `finetune_decoder.py` | `model_type: "decoder"`, `train_type: "sft"` | | Decoder continual pretraining (CPT) | `finetune_decoder.py` | `model_type: "decoder"`, `train_type: "continual_pretrain"` | | Decoder trainable token embeddings | `finetune_decoder.py` | `model_type: "decoder"`, `train_type: "trainable_tokens"` | Example configs are in `examples/example_configs/`. Example SLURM job scripts are in `examples/slurm/`. ## Encoder-decoder experiments On the cluster you typically cannot run training by invoking `python` directly in an interactive terminal — jobs need a GPU and should be submitted through SLURM. Write a shell script (or use one from `examples/slurm/`) with `#SBATCH` headers, `source local_env.sh`, and the `python ... --config ...` command, then submit with `sbatch`. The `python` commands below show what goes inside that script. To launch a job: ```bash sbatch examples/slurm/encoder_decoder_sft_lora.sh ``` Or generate a job script from a config with `submit.py` (see SLURM submission). ### Standard S …