---
language:
- en
license: llama3.2
library_name: transformers
base_model: meditsolutions/Llama-3.2-SUN-2.5B-chat
datasets:
- argilla/OpenHermesPreferences
- argilla/magpie-ultra-v0.1
- argilla/Capybara-Preferences-Filtered
- mlabonne/open-perfectblend
- HuggingFaceTB/everyday-conversations-llama3.1-2k
- WizardLMTeam/WizardLM_evol_instruct_V2_196k
- ProlificAI/social-reasoning-rlhf
pipeline_tag: text-generation
tags:
- TensorBlock
- GGUF
model-index:
- name: Llama-3.2-SUN-2.5B-chat
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 56.04
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 9.41
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 5.06
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 1.23
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 1.11
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 9.04
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=meditsolutions/Llama-3.2-SUN-2.5B-chat
      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>
<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>

## meditsolutions/Llama-3.2-SUN-2.5B-chat - GGUF

This repo contains GGUF format model files for [meditsolutions/Llama-3.2-SUN-2.5B-chat](https://huggingface.co/meditsolutions/Llama-3.2-SUN-2.5B-chat).

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

```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Cutting Knowledge Date: December 2023
Today Date: 25 Nov 2024

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```

## Model file specification

| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Llama-3.2-SUN-2.5B-chat-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q2_K.gguf) | Q2_K | 1.025 GB | smallest, significant quality loss - not recommended for most purposes |
| [Llama-3.2-SUN-2.5B-chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q3_K_S.gguf) | Q3_K_S | 1.173 GB | very small, high quality loss |
| [Llama-3.2-SUN-2.5B-chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q3_K_M.gguf) | Q3_K_M | 1.271 GB | very small, high quality loss |
| [Llama-3.2-SUN-2.5B-chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q3_K_L.gguf) | Q3_K_L | 1.355 GB | small, substantial quality loss |
| [Llama-3.2-SUN-2.5B-chat-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q4_0.gguf) | Q4_0 | 1.466 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Llama-3.2-SUN-2.5B-chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q4_K_S.gguf) | Q4_K_S | 1.475 GB | small, greater quality loss |
| [Llama-3.2-SUN-2.5B-chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q4_K_M.gguf) | Q4_K_M | 1.540 GB | medium, balanced quality - recommended |
| [Llama-3.2-SUN-2.5B-chat-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q5_0.gguf) | Q5_0 | 1.742 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Llama-3.2-SUN-2.5B-chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q5_K_S.gguf) | Q5_K_S | 1.742 GB | large, low quality loss - recommended |
| [Llama-3.2-SUN-2.5B-chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q5_K_M.gguf) | Q5_K_M | 1.780 GB | large, very low quality loss - recommended |
| [Llama-3.2-SUN-2.5B-chat-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q6_K.gguf) | Q6_K | 2.036 GB | very large, extremely low quality loss |
| [Llama-3.2-SUN-2.5B-chat-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-SUN-2.5B-chat-GGUF/blob/main/Llama-3.2-SUN-2.5B-chat-Q8_0.gguf) | Q8_0 | 2.634 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/Llama-3.2-SUN-2.5B-chat-GGUF --include "Llama-3.2-SUN-2.5B-chat-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/Llama-3.2-SUN-2.5B-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```