Hugging Face's logo

bigscience
/
bloomz

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bloom
Eval Results
text-generation-inference
Model card Files
xet
Metrics Community
56
Muennighoff commited on
Commit
028d295
·
1 Parent(s): 99b17ec

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +48 -23
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- license: bigscience-bloom-rail-1.0
3
  datasets:
4
  - bigscience/xP3
 
5
  language:
6
  - ak
7
  - ar
@@ -83,32 +83,57 @@ widget:
83
  example_title: "hi-en fable"
84
  ---
85
 
86
- **Repository**: [bigscience-workshop/bloomz](https://github.com/bigscience-workshop/bloomz)
87
-
88
- # Models
89
-
90
- Multilingual model capable of following user instructions in a variety of languages. Together with our paper [TODO: LINK], we release the following models:
91
-
92
- ----
93
-
94
- - [bloomz](https://huggingface.co/bigscience/bloomz): 176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [xP3](https://huggingface.co/bigscience/xP3)
95
- - [bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1): 7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [xP3](https://huggingface.co/bigscience/xP3)
96
- - [bloomz-3b](https://huggingface.co/bigscience/bloomz-3b): 3B parameter multitask finetuned version of [bloom-3b](https://huggingface.co/bigscience/bloom-3b) on [xP3](https://huggingface.co/bigscience/xP3)
97
- - [bloomz-1b7](https://huggingface.co/bigscience/bloomz-1b7): 1.7B parameter multitask finetuned version of [bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) on [xP3](https://huggingface.co/bigscience/xP3)
98
- - [bloomz-1b1](https://huggingface.co/bigscience/bloomz-1b1): 1.7B parameter multitask finetuned version of [bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) on [xP3](https://huggingface.co/bigscience/xP3)
99
- - [bloomz-560m](https://huggingface.co/bigscience/bloomz-560m): 560M parameter multitask finetuned version of [bloom-560m](https://huggingface.co/bigscience/bloom-560m) on [xP3](https://huggingface.co/bigscience/xP3)
100
-
101
- ----
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
102
 
103
- - [bloomz-mt](https://huggingface.co/bigscience/bloomz-mt): 176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3). **Better than [bloomz](https://huggingface.co/bigscience/bloomz) when prompting in non-english**
104
- - [bloomz-7b1-mt](https://huggingface.co/bigscience/bloomz-7b1-mt): 7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3). **Better than [bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1) when prompting in non-english**
105
 
106
- ----
107
 
108
- - [bloomz-p3](https://huggingface.co/bigscience/bloomz): 176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [bloomz](https://huggingface.co/bigscience/bloomz)**
109
- - [bloomz-7b1-p3](https://huggingface.co/bigscience/bloomz-7b1): 7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1)**
110
 
111
- ----
112
 
113
  # Intended uses
114
 
 
1
  ---
 
2
  datasets:
3
  - bigscience/xP3
4
+ license: bigscience-bloom-rail-1.0
5
  language:
6
  - ak
7
  - ar
 
83
  example_title: "hi-en fable"
84
  ---
85
 
86
+ # Table of Contents
87
+
88
+ 1. [Model Summary](#model=summary)
89
+ 2. [Use](#use)
90
+ 3. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
91
+ 4. [Training Details](#training-details)
92
+ 5. [Evaluation](#evaluation)
93
+ 6. [Environmental Impact](#environmental-impact)
94
+ 7. [Citation](#citation)
95
+ 8. [Model Card Authors](#model-card-authors)
96
+ 9. [How To Get Started With the Model](#how-to-get-started-with-the-model)
97
+
98
+ # Model Summary
99
+
100
+ > We present BLOOMZ & mT0, a family of models capable of following human instructions in hundreds of languages. By finetuning large BLOOM & mT5 pretrained multilingual language models on our multilingual task mixture (xP3), we discover various generalization properties of our finetuned models acrosss tasks and languages.
101
+
102
+ - **Repository:** [bigscience-workshop/xmtf](https://github.com/bigscience-workshop/xmtf)
103
+ - **Paper:** [TODO]
104
+ - **Funded by:** The French government & Hugging Face
105
+ - **Point of Contact:** [Niklas Muennighoff](mailto:[email protected])
106
+ - **BLOOMZ & mT0 Model Family:**
107
+ |Name|Explanation|
108
+ |----|-----------|
109
+ |[bloomz-560m](https://huggingface.co/bigscience/bloomz-560m)| 560M parameter multitask finetuned version of [bloom-560m](https://huggingface.co/bigscience/bloom-560m) on [xP3](https://huggingface.co/bigscience/xP3)|
110
+ |[bloomz-1b1](https://huggingface.co/bigscience/bloomz-1b1)| 1.1B parameter multitask finetuned version of [bloom-1b1](https://huggingface.co/bigscience/bloom-1b1) on [xP3](https://huggingface.co/bigscience/xP3)|
111
+ |[bloomz-1b7](https://huggingface.co/bigscience/bloomz-1b7)| 1.7B parameter multitask finetuned version of [bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) on [xP3](https://huggingface.co/bigscience/xP3)|
112
+ |[bloomz-3b](https://huggingface.co/bigscience/bloomz-3b)| 3B parameter multitask finetuned version of [bloom-3b](https://huggingface.co/bigscience/bloom-3b) on [xP3](https://huggingface.co/bigscience/xP3)|
113
+ |[bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1)|7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [xP3](https://huggingface.co/bigscience/xP3)|
114
+ |[bloomz](https://huggingface.co/bigscience/bloomz)|176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [xP3](https://huggingface.co/bigscience/xP3)|
115
+ |||
116
+ |[bloomz-7b1-mt](https://huggingface.co/bigscience/bloomz-7b1-mt)|7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3mt). **Better than [bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1) when prompting in non-English**|
117
+ |[bloomz-mt](https://huggingface.co/bigscience/bloomz-mt)| 176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3mt). **Better than [bloomz](https://huggingface.co/bigscience/bloomz) when prompting in non-English**|
118
+ |||
119
+ |[bloomz-7b1-p3](https://huggingface.co/bigscience/bloomz-7b1)| 7.1B parameter multitask finetuned version of [bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [bloomz-7b1](https://huggingface.co/bigscience/bloomz-7b1)**|
120
+ |[bloomz-p3](https://huggingface.co/bigscience/bloomz)| 176B parameter multitask finetuned version of [bloom](https://huggingface.co/bigscience/bloom) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [bloomz](https://huggingface.co/bigscience/bloomz)**|
121
+ |||
122
+ |||
123
+ |[mt0-small](https://huggingface.co/bigscience/mt0-xxl)|300M parameter multitask finetuned version of [mt5-small](https://huggingface.co/google/mt5-small) on [xP3](https://huggingface.co/bigscience/xP3)|
124
+ |[mt0-base](https://huggingface.co/bigscience/mt0-xxl)|580M parameter multitask finetuned version of [mt5-base](https://huggingface.co/google/mt5-base) on [xP3](https://huggingface.co/bigscience/xP3)|
125
+ |[mt0-large](https://huggingface.co/bigscience/mt0-xxl)|1.2B parameter multitask finetuned version of [mt5-large](https://huggingface.co/google/mt5-large) on [xP3](https://huggingface.co/bigscience/xP3)|
126
+ |[mt0-xl](https://huggingface.co/bigscience/mt0-xxl)|3.7B parameter multitask finetuned version of [mt5-xl](https://huggingface.co/google/mt5-xl) on [xP3](https://huggingface.co/bigscience/xP3)|
127
+ |[mt0-xxl](https://huggingface.co/bigscience/mt0-xxl)|13B parameter multitask finetuned version of [mt5-xxl](https://huggingface.co/google/mt5-xxl) on [xP3](https://huggingface.co/bigscience/xP3)|
128
+ |||
129
+ |[mt0-xxl-mt](https://huggingface.co/bigscience/mt0-xxl-mt)|13B parameter multitask finetuned version of [mt5-xxl](https://huggingface.co/google/mt5-xxl) on [xP3](https://huggingface.co/bigscience/xP3) & [xP3mt](https://huggingface.co/bigscience/xP3mt). **Better than [mt0-xxl](https://huggingface.co/bigscience/mt0-xxl) when prompting in non-English**|
130
+ |||
131
+ |[mt0-xxl-p3](https://huggingface.co/bigscience/mt0-xxl-p3)| 13B parameter multitask finetuned version of [mt5-xxl](https://huggingface.co/google/mt5-xxl) on [P3](https://huggingface.co/bigscience/P3). **Released for research purposes, performance is inferior to [mt0-xxl](https://huggingface.co/bigscience/mt0-xxl)**|
132
+ |----|-----------|
133
 
 
 
134
 
 
135
 
 
 
136
 
 
137
 
138
  # Intended uses
139