| --- |
| language: |
| - pt |
| license: mit |
| library_name: peft |
| tags: |
| - gptq |
| - ptbr |
| base_model: TheBloke/zephyr-7B-beta-GPTQ |
| revision: gptq-8bit-32g-actorder_True |
| model-index: |
| - name: cesar-ptbr |
| 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: 53.74 |
| name: accuracy |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 46.87 |
| name: accuracy |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 38.27 |
| name: accuracy |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 58.32 |
| name: f1-macro |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 68.49 |
| name: pearson |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 73.81 |
| name: f1-macro |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 83.3 |
| name: f1-macro |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 67.49 |
| name: f1-macro |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| 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: 42.71 |
| name: f1-macro |
| source: |
| url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=matheusrdgsf/cesar-ptbr |
| name: Open Portuguese LLM Leaderboard |
| --- |
| ## Training procedure |
|
|
|
|
| The following `bitsandbytes` quantization config was used during training: |
| - quant_method: gptq |
| - bits: 8 |
| - tokenizer: None |
| - dataset: None |
| - group_size: 32 |
| - damp_percent: 0.1 |
| - desc_act: True |
| - sym: True |
| - true_sequential: True |
| - use_cuda_fp16: False |
| - model_seqlen: 4096 |
| - block_name_to_quantize: model.layers |
| - module_name_preceding_first_block: ['model.embed_tokens'] |
| - batch_size: 1 |
| - pad_token_id: None |
| - disable_exllama: True |
| - max_input_length: None |
| ### Framework versions |
|
|
|
|
|
|
| # Load model AutoModel |
| ```python |
| from peft import PeftModel, PeftConfig |
| from transformers import AutoModelForCausalLM |
| |
| config = PeftConfig.from_pretrained("matheusrdgsf/cesar-ptbr") |
| model = AutoModelForCausalLM.from_pretrained("TheBloke/zephyr-7B-beta-GPTQ", revision="gptq-8bit-32g-actorder_True", device_map='auto') |
| model = PeftModel.from_pretrained(model, "matheusrdgsf/cesar-ptbr") |
| ``` |
|
|
| # Easy inference |
| ```python |
| from transformers import GenerationConfig |
| from transformers import AutoTokenizer |
| |
| tokenizer_model = AutoTokenizer.from_pretrained('TheBloke/zephyr-7B-beta-GPTQ') |
| tokenizer_template = AutoTokenizer.from_pretrained('HuggingFaceH4/zephyr-7b-alpha') |
| |
| generation_config = GenerationConfig( |
| do_sample=True, |
| temperature=0.1, |
| top_p=0.25, |
| top_k=0, |
| max_new_tokens=512, |
| repetition_penalty=1.1, |
| eos_token_id=tokenizer_model.eos_token_id, |
| pad_token_id=tokenizer_model.eos_token_id, |
| ) |
| |
| |
| def get_inference( |
| text, |
| model, |
| tokenizer_model=tokenizer_model, |
| tokenizer_template=tokenizer_template, |
| generation_config=generation_config, |
| ): |
| st_time = time.time() |
| inputs = tokenizer_model( |
| tokenizer_template.apply_chat_template( |
| [ |
| { |
| "role": "system", |
| "content": "Você é um chatbot para indicação de filmes. Responda em português e de maneira educada sugestões de filmes para os usuários.", |
| }, |
| {"role": "user", "content": text}, |
| ], |
| tokenize=False, |
| ), |
| return_tensors="pt", |
| ).to("cuda") |
| |
| outputs = model.generate(**inputs, generation_config=generation_config) |
| |
| print('inference time:', time.time() - st_time) |
| return tokenizer_model.decode(outputs[0], skip_special_tokens=True).split('\n')[-1] |
| |
| get_inference('Poderia indicar filmes de ação de até 2 horas?', model) |
| ``` |
|
|
|
|
| - PEFT 0.5.0 |
|
|
|
|
| # 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/matheusrdgsf/cesar-ptbr) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard) |
|
|
| | Metric | Value | |
| |--------------------------|---------| |
| |Average |**59.22**| |
| |ENEM Challenge (No Images)| 53.74| |
| |BLUEX (No Images) | 46.87| |
| |OAB Exams | 38.27| |
| |Assin2 RTE | 58.32| |
| |Assin2 STS | 68.49| |
| |FaQuAD NLI | 73.81| |
| |HateBR Binary | 83.30| |
| |PT Hate Speech Binary | 67.49| |
| |tweetSentBR | 42.71| |
|
|
|
|
