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-2b4-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Tucano-2b4-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: 42270
+  source: CodeCarbon
+  training_type: pre-training
+  geographical_location: Germany
+  hardware_used: NVIDIA A100-SXM4-80GB
+base_model: TucanoBR/Tucano-2b4-Instruct
+model-index:
+- name: Tucano-2b4-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: 57.66
+      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: 39.92
+      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: 20.43
+      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: 22.81
+      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: 24.83
+      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: 43.39
+      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: 6.31
+      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: 27.7
+      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: 29.18
+      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: tweetSentBR
+      type: eduagarcia-temp/tweetsentbr
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: f1_macro
+      value: 43.11
+      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: 32.05
+      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: 48.28
+      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: 38.44
+      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: 13.0
+      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-2b4-Instruct - GGUF
+
+This repo contains GGUF format model files for [TucanoBR/Tucano-2b4-Instruct](https://huggingface.co/TucanoBR/Tucano-2b4-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-2b4-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q2_K.gguf) | Q2_K | 0.933 GB | smallest, significant quality loss - not recommended for most purposes |
+| [Tucano-2b4-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q3_K_S.gguf) | Q3_K_S | 1.084 GB | very small, high quality loss |
+| [Tucano-2b4-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q3_K_M.gguf) | Q3_K_M | 1.197 GB | very small, high quality loss |
+| [Tucano-2b4-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q3_K_L.gguf) | Q3_K_L | 1.297 GB | small, substantial quality loss |
+| [Tucano-2b4-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q4_0.gguf) | Q4_0 | 1.397 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Tucano-2b4-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q4_K_S.gguf) | Q4_K_S | 1.408 GB | small, greater quality loss |
+| [Tucano-2b4-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q4_K_M.gguf) | Q4_K_M | 1.484 GB | medium, balanced quality - recommended |
+| [Tucano-2b4-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q5_0.gguf) | Q5_0 | 1.693 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Tucano-2b4-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q5_K_S.gguf) | Q5_K_S | 1.693 GB | large, low quality loss - recommended |
+| [Tucano-2b4-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q5_K_M.gguf) | Q5_K_M | 1.737 GB | large, very low quality loss - recommended |
+| [Tucano-2b4-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q6_K.gguf) | Q6_K | 2.007 GB | very large, extremely low quality loss |
+| [Tucano-2b4-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/Tucano-2b4-Instruct-GGUF/blob/main/Tucano-2b4-Instruct-Q8_0.gguf) | Q8_0 | 2.599 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-2b4-Instruct-GGUF --include "Tucano-2b4-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-2b4-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
+```

Tucano-2b4-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d352773c4316a6971ac0a9b0fa93a234dbe8dacc53b0b19c2a87e293cecfaa6
+size 932786752

Tucano-2b4-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c64701c44d2c9fbe6b462a3b898a65f154a3e8e24652a4e8a1345a41a192ba
+size 1296537664

Tucano-2b4-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4d1d3c2eaf7845c4a057fe3594bf3058029e73a836c799503d69f987322415
+size 1197004864

Tucano-2b4-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc99698095abcdd4909142107be1634fad960e2b2d618947397ec52ccb472bf8
+size 1083648064

Tucano-2b4-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305ee92b44bed979b85fae4d3bb7b666b6aa40ce00b6b1f0a78ee167a86d453c
+size 1397427936

Tucano-2b4-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3e03b603ec789d2ec781a922d3aeced03df210b22c31d3b6d3cdbf23a9fcd0
+size 1483597536

Tucano-2b4-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29fb574a21d8b0d2f001a5a392a3e18feb02862fb1506bcd528878f76830f81
+size 1408077536

Tucano-2b4-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cc4b9baad6faa7d07aa5829401a680bb9584013a37d557fd3560f358504ab1
+size 1692750176

Tucano-2b4-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699e571f060410b96191c78263f7db44fb2d030c0e06c214d996dcb9e30853ce
+size 1737140576

Tucano-2b4-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4a90c95de426cdb78f026665ca62ba766dae90c01b7fae3c8c1ed7d9e22fab
+size 1692750176

Tucano-2b4-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cab18a823ea06776439e58c3066e78184ec993d96c6a8dcc967b763a6eeb24b
+size 2006530080

Tucano-2b4-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fddba27cf73774bef811310dc14f1e762ec35709b0c4dd1685fcd7ca7e3938f
+size 2598558112