mbrack commited on
Commit
955e856
1 Parent(s): 3da53c9

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +112 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ - es
6
+ pipeline_tag: text-generation
7
+ ---
8
+
9
+ ![image/png](https://huggingface.co/datasets/malteos/images/resolve/main/occiglot.medium.png)
10
+
11
+ # Occiglot-7B-ES-EN-Instruct
12
+
13
+ > A [polyglot](https://en.wikipedia.org/wiki/Multilingualism#In_individuals) language model for the [Occident](https://en.wikipedia.org/wiki/Occident).
14
+ >
15
+
16
+ **Occiglot-7B-ES-EN-Instruct** is a the instruct version of [occiglot-7b-es-en](https://huggingface.co/occiglot/occiglot-7b-es-en), a generative language model with 7B parameters supporting the Spanish and English and trained by the [Occiglot Research Collective](https://occiglot.github.io/occiglot/).
17
+ It was trained on 160M tokens of additional multilingual and code instructions.
18
+ Note that the model was not safety aligned and might generate problematic outputs.
19
+
20
+ This is the first release of an ongoing open research project for multilingual language models.
21
+ If you want to train a model for your own language or are working on evaluations, please contact us or join our [Discord server](https://discord.gg/wUpvYs4XvM). **We are open for collaborations!**
22
+
23
+
24
+ ### Model details
25
+
26
+ - **Continued-pretraining from:** [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
27
+ - **Model type:** Causal decoder-only transformer language model
28
+ - **Languages:** English, Spanish, and code.
29
+ - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html)
30
+ - **Compute resources:** [DFKI cluster](https://www.dfki.de/en/web)
31
+ - **Contributors:** Manuel Brack, Patrick Schramowski, Pedro Ortiz, Malte Ostendorff, Fabio Barth, Georg Rehm, Kristian Kersting
32
+ - **Research labs:** [Occiglot](https://occiglot.github.io/occiglot/) with support from [SAINT](https://www.dfki.de/en/web/research/research-departments/foundations-of-systems-ai) and [SLT](https://www.dfki.de/en/web/research/research-departments/speech-and-language-technology)
33
+ - **Contact:** [Discord](https://discord.gg/wUpvYs4XvM) [hello@occiglot.org](mailto:hello@occiglot.org)
34
+
35
+ ### How to use
36
+
37
+ The model was trained using the chatml instruction template. You can use the transformers chat template feature for interaction.
38
+ Since the generation relies on some randomness, we
39
+ set a seed for reproducibility:
40
+
41
+ ```python
42
+ >>> from transformers import AutoTokenizer, MistralForCausalLM, set_seed
43
+ >>> tokenizer = AutoTokenizer.from_pretrained("occiglot/occiglot-7b-es-en-instruct")
44
+ >>> model = MistralForCausalLM.from_pretrained('occiglot/occiglot-7b-es-en-instruct') # You may want to use bfloat16 and/or move to GPU here
45
+ >>> set_seed(42)
46
+ >>> messages = [
47
+ >>> {"role": "system", 'content': 'You are a helpful assistant. Please give short and concise answers.'},
48
+ >>> {"role": "user", "content": "¿quién es el presidente del gobierno español?"},
49
+ >>> ]
50
+ >>> tokenized_chat = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_dict=False, return_tensors='pt',)
51
+ >>> set_seed(42)
52
+ >>> outputs = model.generate(tokenized_chat.to('cuda'), max_new_tokens=200,)
53
+ >>> tokenizer.decode(out[0][len(tokenized_chat[0]):])
54
+ 'Actualmente el presidente del gobierno español es Pedro Sánchez Pérez-Castejón'
55
+ ```
56
+
57
+ ## Dataset
58
+
59
+ The training data was split evenly amongst the Spanish and languages based on the total number of tokens.
60
+
61
+ **English and Code**
62
+ - [Open-Hermes-2B](https://huggingface.co/datasets/teknium/OpenHermes-2.5)
63
+
64
+
65
+ **Spanish**
66
+ - [Mentor-ES](https://huggingface.co/datasets/projecte-aina/MentorES)
67
+ - [Squad-es](https://huggingface.co/datasets/squad_es)
68
+ - [OASST-2](https://huggingface.co/datasets/OpenAssistant/oasst2) (Spanish subset)
69
+ - [Aya-Dataset](https://huggingface.co/datasets/CohereForAI/aya_dataset) (Spanish subset)
70
+
71
+ ## Training settings
72
+
73
+ - Full instruction fine-tuning on 8xH100.
74
+ - 0.6 - 4 training epochs (depending on dataset sampling).
75
+ - Framework: [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl)
76
+ - Precision: bf16
77
+ - Optimizer: AdamW
78
+ - Global batch size: 128 (with 8192 context length)
79
+ - Cosine Annealing with Warmup
80
+
81
+
82
+ ## Tokenizer
83
+
84
+ Tokenizer is unchanged from [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
85
+
86
+ ## Evaluation
87
+
88
+ Preliminary evaluation results can be found below.
89
+ Please note that the non-English results are based on partially machine-translated datasets and English prompts ([Belebele](https://huggingface.co/datasets/facebook/belebele) and [Okapi framework](https://github.com/nlp-uoregon/Okapi)) and thus should be interpreted with caution, e.g., biased towards English model performance.
90
+ Currently, we are working on more suitable benchmarks for Spanish, French, German, and Italian.
91
+
92
+ <details>
93
+ <summary>Evaluation results</summary>
94
+
95
+
96
+ </details>
97
+
98
+ ## Acknowledgements
99
+
100
+ The pre-trained model training was supported by a compute grant at the [42 supercomputer](https://hessian.ai/) which is a central component in the development of [hessian AI](https://hessian.ai/), the [AI Innovation Lab](https://hessian.ai/infrastructure/ai-innovationlab/) (funded by the [Hessian Ministry of Higher Education, Research and the Art (HMWK)](https://wissenschaft.hessen.de) & the [Hessian Ministry of the Interior, for Security and Homeland Security (HMinD)](https://innen.hessen.de)) and the [AI Service Centers](https://hessian.ai/infrastructure/ai-service-centre/) (funded by the [German Federal Ministry for Economic Affairs and Climate Action (BMWK)](https://www.bmwk.de/Navigation/EN/Home/home.html)).
101
+ The curation of the training data is partially funded by the [German Federal Ministry for Economic Affairs and Climate Action (BMWK)](https://www.bmwk.de/Navigation/EN/Home/home.html)
102
+ through the project [OpenGPT-X](https://opengpt-x.de/en/) (project no. 68GX21007D).
103
+
104
+
105
+ ## License
106
+
107
+ [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0.html)
108
+
109
+ ## See also
110
+
111
+ - https://huggingface.co/collections/occiglot/occiglot-eu5-7b-v01-65dbed502a6348b052695e01
112
+