File size: 9,390 Bytes
68fbd5e
f0d9d96
 
 
68fbd5e
f7d4026
 
 
 
f0d9d96
f7d4026
 
 
f0d9d96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68fbd5e
4b5e73f
2b055c5
4b5e73f
 
d4672ec
4b5e73f
 
 
526c560
2b055c5
 
4b5e73f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27c28cd
 
4b5e73f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4cd7f88
4b5e73f
4cd7f88
c6d2bb2
4b5e73f
4cd7f88
4b5e73f
4cd7f88
4b5e73f
4cd7f88
4b5e73f
4cd7f88
c6d2bb2
4b5e73f
4cd7f88
4b5e73f
4cd7f88
3b40801
f0d9d96
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d4672ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
---
language:
- pt
license: apache-2.0
library_name: transformers
tags:
- mixtral
- portuguese
- portugues
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
datasets:
- rhaymison/superset
pipeline_tag: text-generation
model-index:
- name: Mistral-8x7b-portuguese-luana
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: ENEM Challenge (No Images)
      type: eduagarcia/enem_challenge
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 69.63
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BLUEX (No Images)
      type: eduagarcia-temp/BLUEX_without_images
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 59.11
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: OAB Exams
      type: eduagarcia/oab_exams
      split: train
      args:
        num_few_shot: 3
    metrics:
    - type: acc
      value: 49.61
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Assin2 RTE
      type: assin2
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: f1_macro
      value: 61.21
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Assin2 STS
      type: eduagarcia/portuguese_benchmark
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: pearson
      value: 79.95
      name: pearson
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: FaQuAD NLI
      type: ruanchaves/faquad-nli
      split: test
      args:
        num_few_shot: 15
    metrics:
    - type: f1_macro
      value: 78.6
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HateBR Binary
      type: ruanchaves/hatebr
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 72.42
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: PT Hate Speech Binary
      type: hate_speech_portuguese
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 73.01
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: tweetSentBR
      type: eduagarcia/tweetsentbr_fewshot
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: f1_macro
      value: 50.9
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-8x7b-portuguese-luana
      name: Open Portuguese LLM Leaderboard
---

# Mistral-8x7b-Quantized-portuguese-luanaa

<p align="center">
  <img src="https://raw.githubusercontent.com/rhaymisonbetini/huggphotos/main/24.webp" width="50%" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
</p>


This model was trained with a superset of 300,000 instructions in Portuguese. 
The model comes to help fill the gap in models in Portuguese. 
Tuned from the Mistral 8x7b and quantized in 4bit for Portuguese, the model was adjusted mainly for instructional tasks.

# How to use

### A100 GPU

You can use the model in its normal form up to 4-bit quantization. Below we will use both approaches.
Remember that verbs are important in your prompt. Tell your model how to act or behave so that you can guide them along the path of their response. 
Important points like these help models (even smaller models like 7b) to perform much better.

```python
!pip install -q -U transformers
!pip install -q -U accelerate
!pip install -q -U bitsandbytes

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model = AutoModelForCausalLM.from_pretrained("rhaymison/Mistral-8x7b-Quantized-portuguese-luana", device_map= {"": 0})
tokenizer = AutoTokenizer.from_pretrained("rhaymison/Mistral-8x7b-Quantized-portuguese-luana")
model.eval()

```

You can use with Pipeline but in this example i will use such as Streaming
```python

inputs = tokenizer([f"""<s>[INST] Abaixo está uma instrução que descreve uma tarefa, juntamente com uma entrada que fornece mais contexto.
Escreva uma resposta que complete adequadamente o pedido.
### instrução: aja como um professor de matemática e me explique porque 2 + 2 = 4.
[/INST]"""], return_tensors="pt")

inputs.to(model.device)

streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=200)

```

If you are having a memory problem such as "CUDA Out of memory", you should use 4-bit or 8-bit quantization.
For the complete model in colab you will need the A100.
If you want to use 4bits or 8bits, T4 or L4 will already solve the problem.

# 4bits example

```python
from transformers import BitsAndBytesConfig
import torch
nb_4bit_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True
)

model = AutoModelForCausalLM.from_pretrained(
    base_model,
    quantization_config=bnb_config,
    device_map={"": 0}
)

```

### LangChain

Extracting a langChain conversation with a drug petition document as context.

* Human: Bom dia. Me informe quais medicamentos são solicitados no texto. Informe também a posologia e o período de tratamento.
    
* Luana: Olá! No texto são solicitados os medicamentos DULOXETINA 30mg,PREGABALINA 100mg ROSUVASTATINA 10mg. 
A posologia e o período de tratamento não são especificados, pois isso deve ser indicado periodicamente pelo médico.
    
* Human: Perfeito. E qual é o valor da causa informado no documento?
    
* Luana: O valor da causa informado no documento é R$ 6.132,00 (seis mil cento e três).
    
* Human: Foi mencionado no texto alguma lei?
    
* Luana: Sim, a Lei Complementar nº 80/94 é mencionada no texto. Ela se refere às prerrogativas institucionais da Defensoria Pública, 
incluindo a intimação pessoal de seus membros, a contagem em dobro dos prazos processuais, a manifestação por cotas nos autos e a dispensa da procuração.
    
* Human: Perfeito! Muito obrigado pela ajuda. Por hora é somente isso =]
    
* Luana: Foi um prazer ajudar! Se você tiver outras dúvidas ou necessitar de mais informações, não hesite em perguntar. Tenha um bom dia!


# Open Portuguese LLM Leaderboard Evaluation Results  

Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/rhaymison/Mistral-8x7b-portuguese-luana) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)

|          Metric          |  Value  |
|--------------------------|---------|
|Average                   |**66.05**|
|ENEM Challenge (No Images)|    69.63|
|BLUEX (No Images)         |    59.11|
|OAB Exams                 |    49.61|
|Assin2 RTE                |    61.21|
|Assin2 STS                |    79.95|
|FaQuAD NLI                |    78.60|
|HateBR Binary             |    72.42|
|PT Hate Speech Binary     |    73.01|
|tweetSentBR               |    50.90|

### Comments

Any idea, help or report will always be welcome.

email: rhaymisoncristian@gmail.com

 <div style="display:flex; flex-direction:row; justify-content:left">
    <a href="https://www.linkedin.com/in/heleno-betini-2b3016175/" target="_blank">
    <img src="https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white">
  </a>
  <a href="https://github.com/rhaymisonbetini" target="_blank">
    <img src="https://img.shields.io/badge/GitHub-100000?style=for-the-badge&logo=github&logoColor=white">
  </a>
 </div>