Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,350 @@
+---
+language:
+- pt
+license: apache-2.0
+library_name: transformers
+tags:
+- text-generation-inference
+- TensorBlock
+- GGUF
+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
+---
+
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;">
+            Feedback and support: TensorBlock's  <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
+        </p>
+    </div>
+</div>
+
+## TucanoBR/Tucano-1b1-Instruct - GGUF
+
+This repo contains GGUF format model files for [TucanoBR/Tucano-1b1-Instruct](https://huggingface.co/TucanoBR/Tucano-1b1-Instruct).
+
+The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
+
+<div style="text-align: left; margin: 20px 0;">
+    <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
+        Run them on the TensorBlock client using your local machine ↗
+    </a>
+</div>
+
+## Prompt template
+
+```
+<instruction>{prompt}</instruction>
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Tucano-1b1-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q2_K.gguf) | Q2_K | 0.432 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Tucano-1b1-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q3_K_S.gguf) | Q3_K_S | 0.499 GB | very small, high quality loss |
+| [Tucano-1b1-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q3_K_M.gguf) | Q3_K_M | 0.548 GB | very small, high quality loss |
+| [Tucano-1b1-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q3_K_L.gguf) | Q3_K_L | 0.592 GB | small, substantial quality loss |
+| [Tucano-1b1-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q4_0.gguf) | Q4_0 | 0.637 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Tucano-1b1-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q4_K_S.gguf) | Q4_K_S | 0.640 GB | small, greater quality loss |
+| [Tucano-1b1-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q4_K_M.gguf) | Q4_K_M | 0.668 GB | medium, balanced quality - recommended |
+| [Tucano-1b1-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q5_0.gguf) | Q5_0 | 0.766 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Tucano-1b1-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q5_K_S.gguf) | Q5_K_S | 0.766 GB | large, low quality loss - recommended |
+| [Tucano-1b1-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q5_K_M.gguf) | Q5_K_M | 0.782 GB | large, very low quality loss - recommended |
+| [Tucano-1b1-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q6_K.gguf) | Q6_K | 0.903 GB | very large, extremely low quality loss |
+| [Tucano-1b1-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Tucano-1b1-Instruct-GGUF/blob/main/Tucano-1b1-Instruct-Q8_0.gguf) | Q8_0 | 1.170 GB | very large, extremely low quality loss - not recommended |
+
+
+## Downloading instruction
+
+### Command line
+
+Firstly, install Huggingface Client
+
+```shell
+pip install -U "huggingface_hub[cli]"
+```
+
+Then, downoad the individual model file the a local directory
+
+```shell
+huggingface-cli download tensorblock/Tucano-1b1-Instruct-GGUF --include "Tucano-1b1-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
+```
+
+If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
+
+```shell
+huggingface-cli download tensorblock/Tucano-1b1-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Tucano-1b1-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cca08f26baa3348c487d55d7fe3400073f6858fb6f4d2140b30592a870f5394
+size 432170304

Tucano-1b1-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9173b23a89e0b7e9b5968d88030d71928208426e1966f1bcea6195c8e24b5816
+size 591566560

Tucano-1b1-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b559a4955923e98411f2edda650f8d54e8c0eebe9f22717b746eb69315df38
+size 548443872

Tucano-1b1-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6acec27b9ce5d765a8ad8ff8aa4963b917f23ae7e7ea36e06987b19058f428ef
+size 499381984

Tucano-1b1-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9b367df4187cc3fea095971999ea87999f5123e9c7c546ebe19dec610d15fc
+size 636766464

Tucano-1b1-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba53cf4e4d8d069137156bd1e6958d839f449cd07f6aaa581e2cb7bc4d7c582
+size 667855104

Tucano-1b1-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5040406412c1c667c17a128726c003f445c8961d7ef20b7acb5f572a25f37baa
+size 639912192

Tucano-1b1-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd3e75df21ac0f8ac4aee28d6176ec6e29a7e83715400d698f9f9ee3997c856
+size 766069504

Tucano-1b1-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8b287595c8264e34e1759e739b1d639d56c49964f7a60af6d8992d4f7a54d5
+size 782084864

Tucano-1b1-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3ae55231a9e325dfcba16a72847518fb397ef046abe76645b463297f0dc6b2
+size 766069504

Tucano-1b1-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba6b77dd0d6243eda85586b42cab9380e00fee73d036f4ed370148decc3fa05
+size 903453984

Tucano-1b1-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17925bd8f1e1e66c31f4bbb859112ec2dadb47dba409866fc30192697f95211
+size 1169851616