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-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-1b1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,329 @@
+---
+language:
+- pt
+license: apache-2.0
+library_name: transformers
+tags:
+- text-generation-inference
+- TensorBlock
+- GGUF
+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: 960000
+  source: CodeCarbon
+  training_type: pre-training
+  geographical_location: Germany
+  hardware_used: NVIDIA A100-SXM4-80GB
+base_model: TucanoBR/Tucano-1b1
+model-index:
+- name: Tucano-1b1
+  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: 58.24
+      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: 34.7
+      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: 21.41
+      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: 23.37
+      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: 25.97
+      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: 60.82
+      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: 24.63
+      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: 29.0
+      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: PT Hate Speech Binary
+      type: hate_speech_portuguese
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 41.19
+      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: 32.18
+      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: 42.84
+      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: 41.59
+      name: bleurt
+    source:
+      url: https://github.com/nlp-uoregon/mlmm-evaluation
+      name: Evaluation Framework for Multilingual Large Language Models
+---
+
+<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 - GGUF
+
+This repo contains GGUF format model files for [TucanoBR/Tucano-1b1](https://huggingface.co/TucanoBR/Tucano-1b1).
+
+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
+
+```
+
+```
+
+## Model file specification
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [Tucano-1b1-Q2_K.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q2_K.gguf) | Q2_K | 0.432 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Tucano-1b1-Q3_K_S.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q3_K_S.gguf) | Q3_K_S | 0.499 GB | very small, high quality loss |
+| [Tucano-1b1-Q3_K_M.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q3_K_M.gguf) | Q3_K_M | 0.548 GB | very small, high quality loss |
+| [Tucano-1b1-Q3_K_L.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q3_K_L.gguf) | Q3_K_L | 0.592 GB | small, substantial quality loss |
+| [Tucano-1b1-Q4_0.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q4_0.gguf) | Q4_0 | 0.637 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Tucano-1b1-Q4_K_S.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q4_K_S.gguf) | Q4_K_S | 0.640 GB | small, greater quality loss |
+| [Tucano-1b1-Q4_K_M.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q4_K_M.gguf) | Q4_K_M | 0.668 GB | medium, balanced quality - recommended |
+| [Tucano-1b1-Q5_0.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q5_0.gguf) | Q5_0 | 0.766 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Tucano-1b1-Q5_K_S.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q5_K_S.gguf) | Q5_K_S | 0.766 GB | large, low quality loss - recommended |
+| [Tucano-1b1-Q5_K_M.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q5_K_M.gguf) | Q5_K_M | 0.782 GB | large, very low quality loss - recommended |
+| [Tucano-1b1-Q6_K.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-Q6_K.gguf) | Q6_K | 0.903 GB | very large, extremely low quality loss |
+| [Tucano-1b1-Q8_0.gguf](https://huggingface.co/tensorblock/Tucano-1b1-GGUF/blob/main/Tucano-1b1-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-GGUF --include "Tucano-1b1-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-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Tucano-1b1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf1a294ec2d3304dc0dde526dd724e9a0f355f74197b28df533fe54a3d589b0
+size 432163872

Tucano-1b1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba6c5f7b8661b26858f1f1ed0585c49c0d94376d5f8c641a34d31b32b583996
+size 591559712

Tucano-1b1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b7d76a47e1030e0b74f95a710028a549322b5ca8670c4f66284d0c95766037
+size 548437024

Tucano-1b1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fafb79fbdad0db0549ec3267b3e8614e58c7def39372b33c63716fb4a2b973
+size 499375136

Tucano-1b1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d230ac79165702b50072ee580e5dbe0192e83be9b02bd8580f8843815beb2eb
+size 636759072

Tucano-1b1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f72ca0274efee91876a4c84d600fc7bfbe3a506d088465f9abe72453b994c9
+size 667847712

Tucano-1b1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a657020682a59c81357457d9cb296146ef5c958361afb2f6d4c15c4e43e92af6
+size 639904800

Tucano-1b1-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb47b1b2b2477317ce821bee33ce1b783db9407837f42f1b2de172f79ef7c176
+size 766061600

Tucano-1b1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01224db32d74bddbfd816cbb2bf6bfb7eb42f2561e14c5d4755b13abe248c8cb
+size 782076960

Tucano-1b1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28443228d8e9bd936a0680caccec4dbfd4777fabef7a8bcb90b8943d1d76c6a3
+size 766061600

Tucano-1b1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bf7c5687511653966fa8de33f6be77acd3ed59783ed4b75f366eb863447e21
+size 903445536

Tucano-1b1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c17116326ef592c32b9fae60d1db0707f85167cda7e0cda2cc465aefb9f6ea
+size 1169841184