--- library_name: transformers tags: - portuguese - phi - text-generation-inference model-index: - name: portuguese-Phi3-Tom-Cat-128k-instruct 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: 51.15 name: accuracy source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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: 42.56 name: accuracy source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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: 39.86 name: accuracy source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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: 88.86 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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 name: pearson source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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: 45.16 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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: 85.92 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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: 65.76 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct 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: 53.32 name: f1-macro source: url: >- https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=rhaymison/portuguese-Phi3-Tom-Cat-128k-instruct name: Open Portuguese LLM Leaderboard license: apache-2.0 datasets: - rhaymison/superset language: - pt pipeline_tag: text-generation --- # Phi-3-portuguese-tom-cat-128k-instruct