Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,325 @@
+---
+language:
+- pt
+license: apache-2.0
+library_name: transformers
+tags:
+- text-generation-inference
+- llama-cpp
+- gguf-my-repo
+datasets:
+- nicholasKluge/instruct-aira-dataset-v3
+- cnmoro/GPT4-500k-Augmented-PTBR-Clean
+- rhaymison/orca-math-portuguese-64k
+- nicholasKluge/reward-aira-dataset
+metrics:
+- perplexity
+pipeline_tag: text-generation
+widget:
+- text: <instruction>Cite algumas bandas de rock brasileiras famosas.</instruction>
+  example_title: Exemplo
+- text: <instruction>Invente uma história sobre um encanador com poderes mágicos.</instruction>
+  example_title: Exemplo
+- text: <instruction>Qual cidade é a capital do estado do Rio Grande do Sul?</instruction>
+  example_title: Exemplo
+- text: <instruction>Diga o nome de uma maravilha culinária característica da cosinha
+    Portuguesa?</instruction>
+  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: 21890
+  source: CodeCarbon
+  training_type: pre-training
+  geographical_location: Germany
+  hardware_used: NVIDIA A100-SXM4-80GB
+base_model: TucanoBR/Tucano-1b1-Instruct
+model-index:
+- name: Tucano-1b1-Instruct
+  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: 56.55
+      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: 35.53
+      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: 21.06
+      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: 26.01
+      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: 26.47
+      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: 67.78
+      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: 8.88
+      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: 31.28
+      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: 41.23
+      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: 22.03
+      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: 30.77
+      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: 43.5
+      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 (PT)
+      type: truthfulqa_pt
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 41.14
+      name: bleurt
+    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: Alpaca-Eval (PT)
+      type: alpaca_eval_pt
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: lc_winrate
+      value: 8.8
+      name: length controlled winrate
+    source:
+      url: https://github.com/tatsu-lab/alpaca_eval
+      name: AlpacaEval
+---
+
+# cnmoro/Tucano-1b1-Instruct-Q8_0-GGUF
+This model was converted to GGUF format from [`TucanoBR/Tucano-1b1-Instruct`](https://huggingface.co/TucanoBR/Tucano-1b1-Instruct) 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-1b1-Instruct) for more details on the model.
+
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+
+```bash
+brew install llama.cpp
+
+```
+Invoke the llama.cpp server or the CLI.
+
+### CLI:
+```bash
+llama-cli --hf-repo cnmoro/Tucano-1b1-Instruct-Q8_0-GGUF --hf-file tucano-1b1-instruct-q8_0.gguf -p "The meaning to life and the universe is"
+```
+
+### Server:
+```bash
+llama-server --hf-repo cnmoro/Tucano-1b1-Instruct-Q8_0-GGUF --hf-file tucano-1b1-instruct-q8_0.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.
+
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo cnmoro/Tucano-1b1-Instruct-Q8_0-GGUF --hf-file tucano-1b1-instruct-q8_0.gguf -p "The meaning to life and the universe is"
+```
+or 
+```
+./llama-server --hf-repo cnmoro/Tucano-1b1-Instruct-Q8_0-GGUF --hf-file tucano-1b1-instruct-q8_0.gguf -c 2048
+```