munish0838 commited on
Commit
22ec9c0
1 Parent(s): cd58d43

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +99 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - Multilingual
4
+ license: mit
5
+ pipeline_tag: text-generation
6
+ base_model: LLaMAX/LLaMAX3-8B-Alpaca
7
+ ---
8
+
9
+ # QuantFactory/LLaMAX3-8B-Alpaca-GGUF
10
+ This is quantized version of [LLaMAX/LLaMAX3-8B-Alpaca](https://huggingface.co/LLaMAX/LLaMAX3-8B-Alpaca) created using llama.cpp
11
+
12
+ # Model Description
13
+ ### Model Sources
14
+
15
+ - **Paper**: LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages
16
+ - **Link**: https://arxiv.org/pdf/2407.05975
17
+ - **Repository**: https://github.com/CONE-MT/LLaMAX/
18
+
19
+ ### Model Description
20
+
21
+ LLaMAX is a language model with powerful multilingual capabilities without loss instruction-following capabilities.
22
+
23
+ We collected extensive training sets in 102 languages for continued pre-training of Llama2 and leveraged the English instruction fine-tuning dataset, Alpaca, to fine-tune its instruction-following capabilities.
24
+
25
+ ### 🔥 Effortless Multilingual Translation with a Simple Prompt
26
+
27
+ LLaMAX supports translation between more than 100 languages, surpassing the performance of similarly scaled LLMs.
28
+
29
+ ```angular2html
30
+ def Prompt_template(query, src_language, trg_language):
31
+ instruction = f'Translate the following sentences from {src_language} to {trg_language}.'
32
+ prompt = (
33
+ 'Below is an instruction that describes a task, paired with an input that provides further context. '
34
+ 'Write a response that appropriately completes the request.\n'
35
+ f'### Instruction:\n{instruction}\n'
36
+ f'### Input:\n{query}\n### Response:'
37
+ )
38
+ return prompt
39
+ ```
40
+
41
+ And then run the following codes to execute translation:
42
+ ```angular2html
43
+ from transformers import AutoTokenizer, LlamaForCausalLM
44
+
45
+ model = LlamaForCausalLM.from_pretrained(PATH_TO_CONVERTED_WEIGHTS)
46
+ tokenizer = AutoTokenizer.from_pretrained(PATH_TO_CONVERTED_TOKENIZER)
47
+
48
+ query = "你好,今天是个好日子"
49
+ prompt = Prompt_template(query, 'Chinese', 'English')
50
+ inputs = tokenizer(prompt, return_tensors="pt")
51
+
52
+ generate_ids = model.generate(inputs.input_ids, max_length=30)
53
+ tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
54
+ # => "Hello, today is a good day"
55
+ ```
56
+
57
+
58
+ ### 🔥 Excellent Translation Performance
59
+
60
+ LLaMAX3-8B-Alpaca achieves an average spBLEU score improvement of over **5 points** compared to the LLaMA3-8B-Alpaca model on the Flores-101 dataset.
61
+
62
+
63
+ | System | Size | en-X (COMET) | en-X (BLEU) | zh-X (COMET)| zh-X (BLEU) | de-X (COMET) | de-X (BLEU) | ne-X (COMET) | ne-X (BLEU) |ar-X (COMET) | ar-X (BLEU) | az-X (COMET) | az-X (BLEU) | ceb-X (COMET) | ceb-X (BLEU)|
64
+ |--------------------|------|--------------------|-------------| ----| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
65
+ | LLaMA3-8B-Alpaca | 8B |67.97|17.23|64.65|10.14|64.67|13.62|62.95|7.96|63.45|11.27|60.61|6.98|55.26|8.52|
66
+ | LLaMAX3-8B-Alpaca | 8B |75.52|22.77|73.16|14.43|73.47|18.95|75.13|15.32|72.29|16.42|72.06|12.41|68.88|15.85|
67
+
68
+
69
+ | System | Size | X-en (COMET) | X-en (BLEU) | X-zh (COMET)| X-zh (BLEU) | X-de (COMET) | X-de (BLEU) | X-ne (COMET) | X-ne (BLEU) |X-ar (COMET) | X-ar (BLEU) | X-az (COMET) | X-az (BLEU) | X-ceb (COMET) | X-ceb (BLEU) |
70
+ |--------------------|------|----------------|-------------| ----| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |--------------|
71
+ | LLaMA3-8B-Alpaca | 8B |77.43|26.55|73.56|13.17|71.59|16.82|46.56|3.83|66.49|10.20|58.30|4.81|52.68|4.18|
72
+ | LLaMAX3-8B-Alpaca | 8B |81.28|31.85|78.34|16.46|76.23|20.64|65.83|14.16|75.84|15.45|70.61|9.32|63.35|12.66|
73
+
74
+
75
+ ### Supported Languages
76
+ Akrikaans (af), Amharic (am), Arabic (ar), Armenian (hy), Assamese (as), Asturian (ast), Azerbaijani (az), Belarusian (be), Bengali (bn), Bosnian (bs), Bulgarian (bg), Burmese (my), Catalan (ca), Cebuano (ceb), Chinese Simpl (zho), Chinese Trad (zho), Croatian (hr), Czech (cs), Danish (da), Dutch (nl), English (en), Estonian (et), Filipino (tl), Finnish (fi), French (fr), Fulah (ff), Galician (gl), Ganda (lg), Georgian (ka), German (de), Greek (el), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Hungarian (hu), Icelandic (is), Igbo (ig), Indonesian (id), Irish (ga), Italian (it), Japanese (ja), Javanese (jv), Kabuverdianu (kea), Kamba (kam), Kannada (kn), Kazakh (kk), Khmer (km), Korean (ko), Kyrgyz (ky), Lao (lo), Latvian (lv), Lingala (ln), Lithuanian (lt), Luo (luo), Luxembourgish (lb), Macedonian (mk), Malay (ms), Malayalam (ml), Maltese (mt), Maori (mi), Marathi (mr), Mongolian (mn), Nepali (ne), Northern Sotho (ns), Norwegian (no), Nyanja (ny), Occitan (oc), Oriya (or), Oromo (om), Pashto (ps), Persian (fa), Polish (pl), Portuguese (pt), Punjabi (pa), Romanian (ro), Russian (ru), Serbian (sr), Shona (sn), Sindhi (sd), Slovak (sk), Slovenian (sl), Somali (so), Sorani Kurdish (ku), Spanish (es), Swahili (sw), Swedish (sv), Tajik (tg), Tamil (ta), Telugu (te), Thai (th), Turkish (tr), Ukrainian (uk), Umbundu (umb), Urdu (ur), Uzbek (uz), Vietnamese (vi), Welsh (cy), Wolof (wo), Xhosa (xh), Yoruba (yo), Zulu (zu)
77
+
78
+ ### Model Index
79
+ We implement multiple versions of the LLaMAX model, the model links are as follows:
80
+
81
+ | Model | LLaMAX | LLaMAX-Alpaca |
82
+ |---------|----------------------------------------------------------|-----------------------------------------------------------------|
83
+ | Llama-2 | [Link](https://huggingface.co/LLaMAX/LLaMAX2-7B) | [Link](https://huggingface.co/LLaMAX/LLaMAX2-7B-Alpaca) |
84
+ | Llama-3 | [Link](https://huggingface.co/LLaMAX/LLaMAX3-8B-8B) | [Link](https://huggingface.co/LLaMAX/LLaMAX3-8B-8B-Alpaca) |
85
+
86
+ ### Model Citation
87
+ If our model helps your work, please cite this paper:
88
+
89
+ ```
90
+ @misc{lu2024llamaxscalinglinguistichorizons,
91
+ title={LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages},
92
+ author={Yinquan Lu and Wenhao Zhu and Lei Li and Yu Qiao and Fei Yuan},
93
+ year={2024},
94
+ eprint={2407.05975},
95
+ archivePrefix={arXiv},
96
+ primaryClass={cs.CL},
97
+ url={https://arxiv.org/abs/2407.05975},
98
+ }
99
+ ```