Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,289 @@
+---
+language:
+- pt
+license: apache-2.0
+library_name: transformers
+tags:
+- text-generation-inference
+- llama-cpp
+- gguf-my-repo
+datasets:
+- TucanoBR/GigaVerbo
+metrics:
+- perplexity
+pipeline_tag: text-generation
+widget:
+- text: A floresta da Amazônia é conhecida por sua
+  example_title: Exemplo
+- text: Uma das coisas que Portugal, Angola, Brasil e Moçambique tem em comum é o
+  example_title: Exemplo
+- text: O Carnaval do Rio de Janeiro é
+  example_title: Exemplo
+inference:
+  parameters:
+    repetition_penalty: 1.2
+    temperature: 0.2
+    top_k: 20
+    top_p: 0.2
+    max_new_tokens: 150
+co2_eq_emissions:
+  emissions: 4475000
+  source: CodeCarbon
+  training_type: pre-training
+  geographical_location: Germany
+  hardware_used: NVIDIA A100-SXM4-80GB
+model-index:
+- name: Tucano-2b4
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: CALAME-PT
+      type: NOVA-vision-language/calame-pt
+      split: all
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc
+      value: 59.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/datasets/NOVA-vision-language/calame-pt
+      name: Context-Aware LAnguage Modeling Evaluation for Portuguese
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: LAMBADA-PT
+      type: TucanoBR/lambada-pt
+      split: train
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc
+      value: 37.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/datasets/TucanoBR/lambada-pt
+      name: LAMBADA-PT
+  - 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: 20.5
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 23.23
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 25.47
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 56.27
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 10
+    metrics:
+    - type: pearson
+      value: 1.93
+      name: pearson
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 43.97
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 29.49
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 41.98
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      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: 58.0
+      name: f1-macro
+    source:
+      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard
+      name: Open Portuguese LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: ARC-Challenge (PT)
+      type: arc_pt
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 30.43
+      name: normalized accuracy
+    source:
+      url: https://github.com/nlp-uoregon/mlmm-evaluation
+      name: Evaluation Framework for Multilingual Large Language Models
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (PT)
+      type: hellaswag_pt
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 47.17
+      name: normalized accuracy
+    source:
+      url: https://github.com/nlp-uoregon/mlmm-evaluation
+      name: Evaluation Framework for Multilingual Large Language Models
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA
+      type: truthfulqa_pt
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 39.3
+      name: bleurt
+    source:
+      url: https://github.com/nlp-uoregon/mlmm-evaluation
+      name: Evaluation Framework for Multilingual Large Language Models
+---
+
+# noxinc/Tucano-2b4-Q4_K_M-GGUF
+This model was converted to GGUF format from [`TucanoBR/Tucano-2b4`](https://huggingface.co/TucanoBR/Tucano-2b4) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+Refer to the [original model card](https://huggingface.co/TucanoBR/Tucano-2b4) for more details on the model.
+## Use with llama.cpp
+
+Install llama.cpp through brew.
+
+```bash
+brew install ggerganov/ggerganov/llama.cpp
+```
+Invoke the llama.cpp server or the CLI.
+
+CLI:
+
+```bash
+llama-cli --hf-repo noxinc/Tucano-2b4-Q4_K_M-GGUF --model tucano-2b4.Q4_K_M.gguf -p "The meaning to life and the universe is"
+```
+
+Server:
+
+```bash
+llama-server --hf-repo noxinc/Tucano-2b4-Q4_K_M-GGUF --model tucano-2b4.Q4_K_M.gguf -c 2048
+```
+
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+
+```
+git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m tucano-2b4.Q4_K_M.gguf -n 128
+```