nunonmg commited on
Commit
add591b
1 Parent(s): afc55d7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -15,13 +15,13 @@ metrics:
15
  - comet
16
  pipeline_tag: translation
17
  ---
18
- # Model Card for TowerInstruct-7B-v0.1
19
 
20
  ## Model Details
21
 
22
  ### Model Description
23
 
24
- TowerInstruct-7B is a language model that results from fine-tuning TowerBase on the TowerBlocks supervised fine-tuning dataset. TowerInstruct-7B-v0.1 is the first model in the series.
25
  The model is trained to handle several translation-related tasks, such as general machine translation (e.g., sentence- and paragraph/document-level translation, terminology-aware translation, context-aware translation), automatic post edition, named-entity recognition, gramatical error correction, and paraphrase generation.
26
  We will release more details in the upcoming technical report.
27
 
@@ -31,7 +31,7 @@ We will release more details in the upcoming technical report.
31
  - **License:** CC-BY-NC-4.0, Llama 2 is licensed under the [LLAMA 2 Community License](https://ai.meta.com/llama/license/), Copyright © Meta Platforms, Inc. All Rights Reserved.
32
  - **Finetuned from model:** [TowerBase](https://huggingface.co/Unbabel/TowerBase-7B-v0.1)
33
 
34
- **Update**: TowerInstruct-7B-v0.2 has more reliable document-level translation capabilities in comparison with TowerInstruct-7B-v0.1. The new version of TowerBlocks used to train v0.2 is also available in the Tower collection.
35
 
36
  ## Intended uses & limitations
37
 
@@ -59,7 +59,7 @@ Here's how you can run the model using the `pipeline()` function from 🤗 Trans
59
  import torch
60
  from transformers import pipeline
61
 
62
- pipe = pipeline("text-generation", model="Unbabel/TowerInstruct-v0.1", torch_dtype=torch.bfloat16, device_map="auto")
63
  # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
64
  messages = [
65
  {"role": "user", "content": "Translate the following text from Portuguese into English.\nPortuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.\nEnglish:"},
@@ -82,11 +82,11 @@ We are currently working on improving quality and consistency on document-level
82
 
83
  ## Bias, Risks, and Limitations
84
 
85
- TowerInstruct-v0.1 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).
86
 
87
  ## Prompt Format
88
 
89
- TowerInstruct-v0.1 was trained using the ChatML prompt templates without any system prompts. An example follows below:
90
  ```
91
  <|im_start|>user
92
  {USER PROMPT}<|im_end|>
 
15
  - comet
16
  pipeline_tag: translation
17
  ---
18
+ # Model Card for TowerInstruct-7B-v0.2
19
 
20
  ## Model Details
21
 
22
  ### Model Description
23
 
24
+ TowerInstruct-7B is a language model that results from fine-tuning TowerBase on the TowerBlocks supervised fine-tuning dataset. TowerInstruct-7B-v0.2 is the first model in the series.
25
  The model is trained to handle several translation-related tasks, such as general machine translation (e.g., sentence- and paragraph/document-level translation, terminology-aware translation, context-aware translation), automatic post edition, named-entity recognition, gramatical error correction, and paraphrase generation.
26
  We will release more details in the upcoming technical report.
27
 
 
31
  - **License:** CC-BY-NC-4.0, Llama 2 is licensed under the [LLAMA 2 Community License](https://ai.meta.com/llama/license/), Copyright © Meta Platforms, Inc. All Rights Reserved.
32
  - **Finetuned from model:** [TowerBase](https://huggingface.co/Unbabel/TowerBase-7B-v0.1)
33
 
34
+ **Update**: TowerInstruct-7B-v0.2 has more reliable document-level translation capabilities in comparison with TowerInstruct-7B-v0.2. The new version of TowerBlocks used to train v0.2 is also available in the Tower collection.
35
 
36
  ## Intended uses & limitations
37
 
 
59
  import torch
60
  from transformers import pipeline
61
 
62
+ pipe = pipeline("text-generation", model="Unbabel/TowerInstruct-v0.2", torch_dtype=torch.bfloat16, device_map="auto")
63
  # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
64
  messages = [
65
  {"role": "user", "content": "Translate the following text from Portuguese into English.\nPortuguese: Um grupo de investigadores lançou um novo modelo para tarefas relacionadas com tradução.\nEnglish:"},
 
82
 
83
  ## Bias, Risks, and Limitations
84
 
85
+ TowerInstruct-v0.2 has not been aligned to human preferences, so the model may generate problematic outputs (e.g., hallucinations, harmful content, or false statements).
86
 
87
  ## Prompt Format
88
 
89
+ TowerInstruct-v0.2 was trained using the ChatML prompt templates without any system prompts. An example follows below:
90
  ```
91
  <|im_start|>user
92
  {USER PROMPT}<|im_end|>