---
license: other
license_name: yi-license
license_link: https://huggingface.co/cognitivecomputations/dolphin-2.2-yi-34b-200k/blob/main/LICENSE
tags:
- TensorBlock
- GGUF
base_model: macadeliccc/SmaugDolphin-60B
model-index:
- name: SmaugDolphin-60B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 73.38
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 86.55
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 76.78
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 67.44
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 83.5
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 70.96
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
      name: Open 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>

[![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co)
[![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi)
[![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2)
[![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock)
[![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock)


## macadeliccc/SmaugDolphin-60B - GGUF

This repo contains GGUF format model files for [macadeliccc/SmaugDolphin-60B](https://huggingface.co/macadeliccc/SmaugDolphin-60B).

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).

## Our projects
<table border="1" cellspacing="0" cellpadding="10">
<tr>
  <th style="font-size: 25px;">Awesome MCP Servers</th>
  <th style="font-size: 25px;">TensorBlock Studio</th>
</tr>
  <tr>
    <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th>
    <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th>
  </tr>
  <tr>
    <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
    <th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
  </tr>
<tr>
  <th>
    <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
      display: inline-block;
      padding: 8px 16px;
      background-color: #FF7F50;
      color: white;
      text-decoration: none;
      border-radius: 6px;
      font-weight: bold;
      font-family: sans-serif;
    ">👀 See what we built 👀</a>
  </th>
  <th>
    <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
      display: inline-block;
      padding: 8px 16px;
      background-color: #FF7F50;
      color: white;
      text-decoration: none;
      border-radius: 6px;
      font-weight: bold;
      font-family: sans-serif;
    ">👀 See what we built 👀</a>
  </th>
</tr>
</table>
## Prompt template

```
[INST] <<SYS>>
{system_prompt}
<</SYS>>

{prompt} [/INST]
```

## Model file specification

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [SmaugDolphin-60B-Q2_K.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q2_K.gguf) | Q2_K | 22.394 GB | smallest, significant quality loss - not recommended for most purposes |
| [SmaugDolphin-60B-Q3_K_S.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q3_K_S.gguf) | Q3_K_S | 26.318 GB | very small, high quality loss |
| [SmaugDolphin-60B-Q3_K_M.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q3_K_M.gguf) | Q3_K_M | 29.237 GB | very small, high quality loss |
| [SmaugDolphin-60B-Q3_K_L.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q3_K_L.gguf) | Q3_K_L | 31.768 GB | small, substantial quality loss |
| [SmaugDolphin-60B-Q4_0.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q4_0.gguf) | Q4_0 | 34.334 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [SmaugDolphin-60B-Q4_K_S.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q4_K_S.gguf) | Q4_K_S | 34.594 GB | small, greater quality loss |
| [SmaugDolphin-60B-Q4_K_M.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q4_K_M.gguf) | Q4_K_M | 36.661 GB | medium, balanced quality - recommended |
| [SmaugDolphin-60B-Q5_0.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q5_0.gguf) | Q5_0 | 41.878 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [SmaugDolphin-60B-Q5_K_S.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q5_K_S.gguf) | Q5_K_S | 41.878 GB | large, low quality loss - recommended |
| [SmaugDolphin-60B-Q5_K_M.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q5_K_M.gguf) | Q5_K_M | 43.077 GB | large, very low quality loss - recommended |
| [SmaugDolphin-60B-Q6_K.gguf](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q6_K.gguf) | Q6_K | 49.893 GB | very large, extremely low quality loss |
| [SmaugDolphin-60B-Q8_0](https://huggingface.co/tensorblock/SmaugDolphin-60B-GGUF/blob/main/SmaugDolphin-60B-Q8_0) | Q8_0 | 64.621 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/SmaugDolphin-60B-GGUF --include "SmaugDolphin-60B-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/SmaugDolphin-60B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```