| license: other | |
| language: | |
| - en | |
| pipeline_tag: text-generation | |
| inference: false | |
| tags: | |
| - transformers | |
| - gguf | |
| - imatrix | |
| - ALMA-13B-R | |
| Quantizations of https://huggingface.co/haoranxu/ALMA-13B-R | |
| # From original readme | |
| 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) | |
| ``` |