Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Description

imatrix.dat just for en or zh(beacuse of the data I used to imatrix)

For this models,if you want more language, it seems that it would be better to quantize directly without using imatrix. (Q5_K_S is better.)

If you want Chinese - English translate, you can use the imatrix.dat from here.

I just made a gguf file for my own use, and then share it, please support the original author haoranxu

This repo contains GGUF format model files for haoranxu/ALMA-7B-R

That's all I can do with the bad network cable, short text translation works well, long text may encounter some problems, it is recommended to use it with a sentence splitting plugin (e.g. Immersive Translate).

Q3KM will lead to an increase in translation speed and a decrease in quality, if you need better translation quality, it is recommended to use the original version (7B-R, 13B-R)

prompt="Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"

Sensitive to the prescribed formatting, deformatting may lead to strange output, please refer to the perset.json (For LM Studio) in the file for details



the original model card:

license: mit

ALMA-R builds upon ALMA models, with further LoRA fine-tuning with our proposed Contrastive Preference Optimization (CPO) as opposed to the Supervised Fine-tuning used in ALMA. CPO fine-tuning requires our triplet preference data for preference learning. ALMA-R now can matches or even exceeds GPT-4 or WMT winners!

@misc{xu2024contrastive,
      title={Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation}, 
      author={Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
      year={2024},
      eprint={2401.08417},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
@misc{xu2023paradigm,
      title={A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models}, 
      author={Haoran Xu and Young Jin Kim and Amr Sharaf and Hany Hassan Awadalla},
      year={2023},
      eprint={2309.11674},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Download ALMA(-R) Models and Dataset 🚀

We release six translation models presented in the paper:

  • ALMA-7B
  • ALMA-7B-LoRA
  • ALMA-7B-R (NEW!): Further LoRA fine-tuning upon ALMA-7B-LoRA with contrastive preference optimization.
  • ALMA-13B
  • ALMA-13B-LoRA
  • ALMA-13B-R (NEW!): Further LoRA fine-tuning upon ALMA-13B-LoRA with contrastive preference optimization (BEST MODEL!).

Model checkpoints are released at huggingface:

Note that ALMA-7B-Pretrain and ALMA-13B-Pretrain are NOT translation models. They only experience stage 1 monolingual fine-tuning (20B tokens for the 7B model and 12B tokens for the 13B model), and should be utilized in conjunction with their LoRA models.

Datasets used by ALMA and ALMA-R are also released at huggingface now (NEW!)

Datasets Train / Validation Test
Human-Written Parallel Data (ALMA) train and validation WMT'22
Triplet Preference Data train WMT'22 and WMT'23

A quick start to use our best system (ALMA-13B-R) for translation. An example of translating "我爱机器翻译。" into English:

import torch
from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer

# Load base model and LoRA weights
model = AutoModelForCausalLM.from_pretrained("haoranxu/ALMA-13B-R", torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("haoranxu/ALMA-13B-R", padding_side='left')

# Add the source sentence into the prompt template
prompt="Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"
input_ids = tokenizer(prompt, return_tensors="pt", padding=True, max_length=40, truncation=True).input_ids.cuda()

# Translation
with torch.no_grad():
    generated_ids = model.generate(input_ids=input_ids, num_beams=5, max_new_tokens=20, do_sample=True, temperature=0.6, top_p=0.9)
outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
print(outputs)

Please find more details in our GitHub repository

Downloads last month
114
GGUF
Model size
6.74B params
Architecture
llama

3-bit

Inference API
Unable to determine this model's library. Check the docs .