File size: 10,674 Bytes
ee7e47a 4074705 ee7e47a f9be4a4 9709ef7 f9be4a4 4074705 ee7e47a d6ef179 ee7e47a f9be4a4 364ef5b f9be4a4 ee7e47a 00bacea 509500d ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a f9be4a4 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 54b8700 ee7e47a 4074705 e9ed2cb 94c9f55 e9ed2cb 94c9f55 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
---
language:
- pt
license: apache-2.0
library_name: transformers
tags:
- Misral
- Portuguese
- 7b
- chat
- portugues
base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
- rhaymison/ultrachat-easy-use
pipeline_tag: text-generation
model-index:
- name: Mistral-portuguese-luana-7b-chat
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: 59.13
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
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: 49.24
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
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: 36.58
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
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: 90.47
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
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: 76.55
name: pearson
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
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: 66.75
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
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: 77.46
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
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: 69.45
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: tweetSentBR
type: eduagarcia-temp/tweetsentbr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 59.63
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/Mistral-portuguese-luana-7b-chat
name: Open Portuguese LLM Leaderboard
---
# Mistral-portuguese-luana-7b-chat
<p align="center">
<img src="https://raw.githubusercontent.com/rhaymisonbetini/huggphotos/main/luana-chat.webp" width="50%" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
</p>
This model was trained with a superset of 250,000 chat in Portuguese.
The model comes to help fill the gap in models in Portuguese. Tuned from the Mistral 7b, the model was adjusted mainly for chat.
# How to use
### FULL MODEL : A100
### HALF MODEL: L4
### 8bit or 4bit : T4 or V100
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-portuguese-luana-7b-chat", device_map= {"": 0})
tokenizer = AutoTokenizer.from_pretrained("rhaymison/Mistral-portuguese-luana-7b-chat")
model.eval()
```
You can use with Pipeline but in this example i will use such as Streaming
```python
inputs = tokenizer([f"""<s>[INST] Estou pensando em levar minha esposa e meu gatinha para fazer algo diferente. Você teria alguma coisa em mente ?.
[/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=128)
```
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
<div style="background-color:#f0f0f0; padding:10px; border-radius:10px; font-family: 'Arial';">
<p><strong><span style="color:#3366cc;">Human:</span></strong> Ola Luana, estou precisando de umas dicas para o final de semana.
Poderia me ajudar ?</p>
<p><strong><span style="color:#ff6600;">Luana:</span></strong> Olá! Claro, ficarei feliz em ajudá-lo. O que você tem em mente para o final de semana?</p>
<p><strong><span style="color:#3366cc;">Human:</span></strong> Estou pensando em levar minha esposa e meu gatinha para fazer algo diferente.
Você teria alguma coisa em mente ?</p>
<p><strong><span style="color:#ff6600;">Luana:</span></strong> Claro! Você pode considerar fazer um piquenique na praia, visitar um museu
ou fazer uma caminhada na natureza. O que você e sua esposa gostam de fazer juntos?</p>
<p><strong><span style="color:#3366cc;">Human:</span></strong> Eu e minha esposa gostamos muito de caminhadas.
Temos uma mochila que carregamos nosso gatinha para todo lado.</p>
<p><strong><span style="color:#ff6600;">Luana:</span></strong> Parece ótimo! Você pode considerar fazer uma caminhada em um parque local ou reserva natural. Você
também pode pesquisar trilhas mais longas para fazer em um fim de semana.
Além disso, você pode trazer um piquenique com você para saborear durante a caminhada.</p>
<p><strong><span style="color:#3366cc;">Human:</span></strong> Otimas ideias voce tem me dado. O que será que é gostoso levar em um piquenique ?</p>
<p><strong><span style="color:#ff6600;">Luana:</span></strong> Você pode trazer sanduíches, frutas, vegetais, queijo e biscoitos.
Você também pode trazer uma garrafa de água ou um refrigerante para beber.
Além disso, você pode trazer um saco de lixo para descartar resíduos de maneira responsável.</p>
<p><strong><span style="color:#3366cc;">Human:</span></strong> Olha só que dica bacana. Realmente devo levar uma sacola para nao descartar
nada na Natureza e assim me divertir com minha esposa.</p>
<p><strong><span style="color:#ff6600;">Luana:</span></strong> Sim, é importante descartar resíduos de maneira responsável e proteger o meio ambiente.
Você pode considerar fazer um piquenique em um parque local ou reserva natural onde
possa descartar resíduos de maneira responsável.</p>
<p><strong><span style="color:#3366cc;">Human:</span></strong> Perfeito. Muito Obrigado Luana. Otimas dicas. Até a proxima !</p>
<p><strong><span style="color:#ff6600;">Luana:</span></strong> De nada! Fique em contato se precisar de mais ajuda. Tenha um ótimo fim de semana!</p>
</div>
# [Open Portuguese LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/rhaymison/Mistral-portuguese-luana-7b-chat)
| Metric | Value |
|--------------------------|---------|
|Average |**65.03**|
|ENEM Challenge (No Images)| 59.13|
|BLUEX (No Images) | 49.24|
|OAB Exams | 36.58|
|Assin2 RTE | 90.47|
|Assin2 STS | 76.55|
|FaQuAD NLI | 66.75|
|HateBR Binary | 77.46|
|PT Hate Speech Binary | 69.45|
|tweetSentBR | 59.63|
### Comments
Any idea, help or report will always be welcome.
email: [email protected]
<div style="display:flex; flex-direction:row; justify-content:left">
<a href="https://www.linkedin.com/in/rhaymison-cristian-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>
|