---
language:
- pt
license: apache-2.0
library_name: transformers
tags:
- text-generation-inference
- TensorBlock
- GGUF
datasets:
- nicholasKluge/Pt-Corpus-Instruct
metrics:
- perplexity
pipeline_tag: text-generation
widget:
- text: 'A PUCRS é uma universidade '
  example_title: Exemplo
- text: A muitos anos atrás, em uma galáxia muito distante, vivia uma raça de
  example_title: Exemplo
- text: Em meio a um escândalo, a frente parlamentar pediu ao Senador Silva para
  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: 5600
  source: CodeCarbon
  training_type: pre-training
  geographical_location: Germany
  hardware_used: NVIDIA A100-SXM4-40GB
base_model: nicholasKluge/TeenyTinyLlama-160m
model-index:
- name: TeenyTinyLlama-160m
  results:
  - 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: 19.24
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      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: 23.09
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      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: 22.37
      name: accuracy
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      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: 53.97
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      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: 15
    metrics:
    - type: pearson
      value: 0.24
      name: pearson
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      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?query=nicholasKluge/TeenyTinyLlama-160m
      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: 36.92
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      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: 42.63
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      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: 11.39
      name: f1-macro
    source:
      url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=nicholasKluge/TeenyTinyLlama-160m
      name: Open Portuguese LLM Leaderboard
---

<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>

## nicholasKluge/TeenyTinyLlama-160m - GGUF

This repo contains GGUF format model files for [nicholasKluge/TeenyTinyLlama-160m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m).

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 |
| -------- | ---------- | --------- | ----------- |
| [TeenyTinyLlama-160m-Q2_K.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q2_K.gguf) | Q2_K | 0.071 GB | smallest, significant quality loss - not recommended for most purposes |
| [TeenyTinyLlama-160m-Q3_K_S.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q3_K_S.gguf) | Q3_K_S | 0.080 GB | very small, high quality loss |
| [TeenyTinyLlama-160m-Q3_K_M.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q3_K_M.gguf) | Q3_K_M | 0.086 GB | very small, high quality loss |
| [TeenyTinyLlama-160m-Q3_K_L.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q3_K_L.gguf) | Q3_K_L | 0.091 GB | small, substantial quality loss |
| [TeenyTinyLlama-160m-Q4_0.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q4_0.gguf) | Q4_0 | 0.099 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [TeenyTinyLlama-160m-Q4_K_S.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q4_K_S.gguf) | Q4_K_S | 0.099 GB | small, greater quality loss |
| [TeenyTinyLlama-160m-Q4_K_M.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q4_K_M.gguf) | Q4_K_M | 0.103 GB | medium, balanced quality - recommended |
| [TeenyTinyLlama-160m-Q5_0.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q5_0.gguf) | Q5_0 | 0.116 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [TeenyTinyLlama-160m-Q5_K_S.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q5_K_S.gguf) | Q5_K_S | 0.116 GB | large, low quality loss - recommended |
| [TeenyTinyLlama-160m-Q5_K_M.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q5_K_M.gguf) | Q5_K_M | 0.118 GB | large, very low quality loss - recommended |
| [TeenyTinyLlama-160m-Q6_K.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q6_K.gguf) | Q6_K | 0.134 GB | very large, extremely low quality loss |
| [TeenyTinyLlama-160m-Q8_0.gguf](https://huggingface.co/tensorblock/TeenyTinyLlama-160m-GGUF/blob/main/TeenyTinyLlama-160m-Q8_0.gguf) | Q8_0 | 0.173 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/TeenyTinyLlama-160m-GGUF --include "TeenyTinyLlama-160m-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/TeenyTinyLlama-160m-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```