---
datasets:
- bigscience/xP3
license: bigscience-bloom-rail-1.0
language:
- ak
- ar
- as
- bm
- bn
- ca
- code
- en
- es
- eu
- fon
- fr
- gu
- hi
- id
- ig
- ki
- kn
- lg
- ln
- ml
- mr
- ne
- nso
- ny
- or
- pa
- pt
- rn
- rw
- sn
- st
- sw
- ta
- te
- tn
- ts
- tum
- tw
- ur
- vi
- wo
- xh
- yo
- zh
- zu
programming_language:
- C
- C++
- C#
- Go
- Java
- JavaScript
- Lua
- PHP
- Python
- Ruby
- Rust
- Scala
- TypeScript
pipeline_tag: text-generation
widget:
- text: 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。Would you rate the previous
    review as positive, neutral or negative?
  example_title: zh-en sentiment
- text: 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评？
  example_title: zh-zh sentiment
- text: Suggest at least five related search terms to "Mạng neural nhân tạo".
  example_title: vi-en query
- text: Proposez au moins cinq mots clés concernant «Réseau de neurones artificiels».
  example_title: fr-fr query
- text: Explain in a sentence in Telugu what is backpropagation in neural networks.
  example_title: te-en qa
- text: Why is the sky blue?
  example_title: en-en qa
- text: 'Write a fairy tale about a troll saving a princess from a dangerous dragon.
    The fairy tale is a masterpiece that has achieved praise worldwide and its moral
    is "Heroes Come in All Shapes and Sizes". Story (in Spanish):'
  example_title: es-en fable
- text: 'Write a fable about wood elves living in a forest that is suddenly invaded
    by ogres. The fable is a masterpiece that has achieved praise worldwide and its
    moral is "Violence is the last refuge of the incompetent". Fable (in Hindi):'
  example_title: hi-en fable
tags:
- TensorBlock
- GGUF
base_model: bigscience/bloomz-3b
model-index:
- name: bloomz-3b1
  results:
  - task:
      type: Coreference resolution
    dataset:
      name: Winogrande XL (xl)
      type: winogrande
      config: xl
      split: validation
      revision: a80f460359d1e9a67c006011c94de42a8759430c
    metrics:
    - type: Accuracy
      value: 53.67
  - task:
      type: Coreference resolution
    dataset:
      name: XWinograd (en)
      type: Muennighoff/xwinograd
      config: en
      split: test
      revision: 9dd5ea5505fad86b7bedad667955577815300cee
    metrics:
    - type: Accuracy
      value: 59.23
  - task:
      type: Coreference resolution
    dataset:
      name: XWinograd (fr)
      type: Muennighoff/xwinograd
      config: fr
      split: test
      revision: 9dd5ea5505fad86b7bedad667955577815300cee
    metrics:
    - type: Accuracy
      value: 53.01
  - task:
      type: Coreference resolution
    dataset:
      name: XWinograd (jp)
      type: Muennighoff/xwinograd
      config: jp
      split: test
      revision: 9dd5ea5505fad86b7bedad667955577815300cee
    metrics:
    - type: Accuracy
      value: 52.45
  - task:
      type: Coreference resolution
    dataset:
      name: XWinograd (pt)
      type: Muennighoff/xwinograd
      config: pt
      split: test
      revision: 9dd5ea5505fad86b7bedad667955577815300cee
    metrics:
    - type: Accuracy
      value: 53.61
  - task:
      type: Coreference resolution
    dataset:
      name: XWinograd (ru)
      type: Muennighoff/xwinograd
      config: ru
      split: test
      revision: 9dd5ea5505fad86b7bedad667955577815300cee
    metrics:
    - type: Accuracy
      value: 53.97
  - task:
      type: Coreference resolution
    dataset:
      name: XWinograd (zh)
      type: Muennighoff/xwinograd
      config: zh
      split: test
      revision: 9dd5ea5505fad86b7bedad667955577815300cee
    metrics:
    - type: Accuracy
      value: 60.91
  - task:
      type: Natural language inference
    dataset:
      name: ANLI (r1)
      type: anli
      config: r1
      split: validation
      revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
    metrics:
    - type: Accuracy
      value: 40.1
  - task:
      type: Natural language inference
    dataset:
      name: ANLI (r2)
      type: anli
      config: r2
      split: validation
      revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
    metrics:
    - type: Accuracy
      value: 36.8
  - task:
      type: Natural language inference
    dataset:
      name: ANLI (r3)
      type: anli
      config: r3
      split: validation
      revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
    metrics:
    - type: Accuracy
      value: 40.0
  - task:
      type: Natural language inference
    dataset:
      name: SuperGLUE (cb)
      type: super_glue
      config: cb
      split: validation
      revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
    metrics:
    - type: Accuracy
      value: 75.0
  - task:
      type: Natural language inference
    dataset:
      name: SuperGLUE (rte)
      type: super_glue
      config: rte
      split: validation
      revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
    metrics:
    - type: Accuracy
      value: 76.17
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (ar)
      type: xnli
      config: ar
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 53.29
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (bg)
      type: xnli
      config: bg
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 43.82
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (de)
      type: xnli
      config: de
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 45.26
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (el)
      type: xnli
      config: el
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 42.61
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (en)
      type: xnli
      config: en
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 57.31
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (es)
      type: xnli
      config: es
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 56.14
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (fr)
      type: xnli
      config: fr
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 55.78
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (hi)
      type: xnli
      config: hi
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 51.49
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (ru)
      type: xnli
      config: ru
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 47.11
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (sw)
      type: xnli
      config: sw
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 47.83
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (th)
      type: xnli
      config: th
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 42.93
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (tr)
      type: xnli
      config: tr
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 37.23
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (ur)
      type: xnli
      config: ur
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 49.04
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (vi)
      type: xnli
      config: vi
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 53.98
  - task:
      type: Natural language inference
    dataset:
      name: XNLI (zh)
      type: xnli
      config: zh
      split: validation
      revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
    metrics:
    - type: Accuracy
      value: 54.18
  - task:
      type: Program synthesis
    dataset:
      name: HumanEval
      type: openai_humaneval
      config: None
      split: test
      revision: e8dc562f5de170c54b5481011dd9f4fa04845771
    metrics:
    - type: Pass@1
      value: 6.29
    - type: Pass@10
      value: 11.94
    - type: Pass@100
      value: 19.06
  - task:
      type: Sentence completion
    dataset:
      name: StoryCloze (2016)
      type: story_cloze
      config: '2016'
      split: validation
      revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
    metrics:
    - type: Accuracy
      value: 87.33
  - task:
      type: Sentence completion
    dataset:
      name: SuperGLUE (copa)
      type: super_glue
      config: copa
      split: validation
      revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
    metrics:
    - type: Accuracy
      value: 76.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (et)
      type: xcopa
      config: et
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 53.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (ht)
      type: xcopa
      config: ht
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 64.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (id)
      type: xcopa
      config: id
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 70.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (it)
      type: xcopa
      config: it
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 53.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (qu)
      type: xcopa
      config: qu
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 56.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (sw)
      type: xcopa
      config: sw
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 66.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (ta)
      type: xcopa
      config: ta
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 59.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (th)
      type: xcopa
      config: th
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 63.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (tr)
      type: xcopa
      config: tr
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 61.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (vi)
      type: xcopa
      config: vi
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 77.0
  - task:
      type: Sentence completion
    dataset:
      name: XCOPA (zh)
      type: xcopa
      config: zh
      split: validation
      revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
    metrics:
    - type: Accuracy
      value: 73.0
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (ar)
      type: Muennighoff/xstory_cloze
      config: ar
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 80.61
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (es)
      type: Muennighoff/xstory_cloze
      config: es
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 85.9
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (eu)
      type: Muennighoff/xstory_cloze
      config: eu
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 70.95
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (hi)
      type: Muennighoff/xstory_cloze
      config: hi
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 78.89
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (id)
      type: Muennighoff/xstory_cloze
      config: id
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 82.99
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (my)
      type: Muennighoff/xstory_cloze
      config: my
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 49.9
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (ru)
      type: Muennighoff/xstory_cloze
      config: ru
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 61.42
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (sw)
      type: Muennighoff/xstory_cloze
      config: sw
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 69.69
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (te)
      type: Muennighoff/xstory_cloze
      config: te
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 73.66
  - task:
      type: Sentence completion
    dataset:
      name: XStoryCloze (zh)
      type: Muennighoff/xstory_cloze
      config: zh
      split: validation
      revision: 8bb76e594b68147f1a430e86829d07189622b90d
    metrics:
    - type: Accuracy
      value: 84.32
---

<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>

## bigscience/bloomz-3b - GGUF

This repo contains GGUF format model files for [bigscience/bloomz-3b](https://huggingface.co/bigscience/bloomz-3b).

The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](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 |
| -------- | ---------- | --------- | ----------- |
| [bloomz-3b-Q2_K.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q2_K.gguf) | Q2_K | 1.516 GB | smallest, significant quality loss - not recommended for most purposes |
| [bloomz-3b-Q3_K_S.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q3_K_S.gguf) | Q3_K_S | 1.707 GB | very small, high quality loss |
| [bloomz-3b-Q3_K_M.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q3_K_M.gguf) | Q3_K_M | 1.905 GB | very small, high quality loss |
| [bloomz-3b-Q3_K_L.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q3_K_L.gguf) | Q3_K_L | 2.016 GB | small, substantial quality loss |
| [bloomz-3b-Q4_0.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q4_0.gguf) | Q4_0 | 2.079 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [bloomz-3b-Q4_K_S.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q4_K_S.gguf) | Q4_K_S | 2.088 GB | small, greater quality loss |
| [bloomz-3b-Q4_K_M.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q4_K_M.gguf) | Q4_K_M | 2.235 GB | medium, balanced quality - recommended |
| [bloomz-3b-Q5_0.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q5_0.gguf) | Q5_0 | 2.428 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [bloomz-3b-Q5_K_S.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q5_K_S.gguf) | Q5_K_S | 2.428 GB | large, low quality loss - recommended |
| [bloomz-3b-Q5_K_M.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q5_K_M.gguf) | Q5_K_M | 2.546 GB | large, very low quality loss - recommended |
| [bloomz-3b-Q6_K.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q6_K.gguf) | Q6_K | 2.799 GB | very large, extremely low quality loss |
| [bloomz-3b-Q8_0.gguf](https://huggingface.co/tensorblock/bloomz-3b-GGUF/blob/main/bloomz-3b-Q8_0.gguf) | Q8_0 | 3.621 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/bloomz-3b-GGUF --include "bloomz-3b-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/bloomz-3b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```