---
base_model: TeeZee/DarkForest-20B-v2.0
base_model_relation: quantized
quantized_by: ArtusDev
license: other
tags:
- merge
- not-for-all-audiences
- exl3
license_name: microsoft-research-license
model-index:
- name: DarkForest-20B-v2.0
  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: 63.74
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
      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: 86.32
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
      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: 59.79
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
      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: 56.14
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
      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: 77.9
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
      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: 23.28
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=TeeZee/DarkForest-20B-v2.0
      name: Open LLM Leaderboard
---

## EXL3 Quants of TeeZee/DarkForest-20B-v2.0

EXL3 quants of [TeeZee/DarkForest-20B-v2.0](https://huggingface.co/TeeZee/DarkForest-20B-v2.0) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization.

### Quants
| Quant(Revision) | Bits per Weight | Head Bits |
| -------- | ---------- | --------- |
| [2.5_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/2.5bpw_H6) | 2.5 | 6 |
| [3.0_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/3.0bpw_H6) | 3.0 | 6 |
| [3.5_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/3.5bpw_H6) | 3.5 | 6 |
| [4.0_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/4.0bpw_H6) | 4.0 | 6 |
| [4.5_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/4.5bpw_H6) | 4.5 | 6 |
| [5.0_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/5.0bpw_H6) | 5.0 | 6 |
| [6.0_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/6.0bpw_H6) | 6.0 | 6 |
| [8.0_H6](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/8.0bpw_H6) | 8.0 | 6 |
| [8.0_H8](https://huggingface.co/ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3/tree/8.0bpw_H8) | 8.0 | 8 |

### Downloading quants with huggingface-cli

<details>
  <summary>Click to view download instructions</summary>

Install hugginface-cli:

```bash
pip install -U "huggingface_hub[cli]"
```

Download quant by targeting the specific quant revision (branch):

```
huggingface-cli download ArtusDev/TeeZee_DarkForest-20B-v2.0-EXL3 --revision "5bpw_H6" --local-dir ./
```
</details>