--- 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

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 in Portuguese, 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"""[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

Human: Ola Luana, estou precisando de umas dicas para o final de semana. Poderia me ajudar ?

Luana: Olá! Claro, ficarei feliz em ajudá-lo. O que você tem em mente para o final de semana?

Human: Estou pensando em levar minha esposa e meu gatinha para fazer algo diferente. Você teria alguma coisa em mente ?

Luana: 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?

Human: Eu e minha esposa gostamos muito de caminhadas. Temos uma mochila que carregamos nosso gatinha para todo lado.

Luana: 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.

Human: Otimas ideias voce tem me dado. O que será que é gostoso levar em um piquenique ?

Luana: 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.

Human: Olha só que dica bacana. Realmente devo levar uma sacola para nao descartar nada na Natureza e assim me divertir com minha esposa.

Luana: 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.

Human: Perfeito. Muito Obrigado Luana. Otimas dicas. Até a proxima !

Luana: De nada! Fique em contato se precisar de mais ajuda. Tenha um ótimo fim de semana!

# [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: rhaymisoncristian@gmail.com