zaenalium_-_MicroMistral-Indo-400M-exl2

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MicroMistral-Indo-400M - EXL2

• Model creator: https://huggingface.co/zaenalium/
• Original model: https://huggingface.co/zaenalium/MicroMistral-Indo-400M/

Available sizes

| Branch | Bits | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ | | 8_0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | 6_5 | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, recommended. | | 5_0 | 5.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. | | 4_25 | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. | | 3_5 | 3.5 | Lower quality, only use if you have to. |

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/zaenalium_-_MicroMistral-Indo-400M-exl2 MicroMistral-Indo-400M-6_5

With huggingface hub:

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch: Linux:

huggingface-cli download zaenalium_-_MicroMistral-Indo-400M-exl2 --revision 6_5 --local-dir MicroMistral-Indo-400M-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download zaenalium_-_MicroMistral-Indo-400M-exl2 --revision 6_5 --local-dir MicroMistral-Indo-400M-6.5 --local-dir-use-symlinks False

Original model description:

tags:

• generated_from_trainer datasets:
• MBZUAI/Bactrian-X metrics:
• accuracy model-index:
• name: Mistral-Indo results:
  • task: name: Causal Language Modeling type: text-generation dataset: name: MBZUAI/Bactrian-X id type: MBZUAI/Bactrian-X args: id metrics:
    • name: Accuracy type: accuracy value: 0.2462286333254075

---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

Mistral-Indo

This model was trained from scratch on the MBZUAI/Bactrian-X id dataset. It achieves the following results on the evaluation set:

• Loss: 5.4269
• Accuracy: 0.2462

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20.0

Training results

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.2
• Datasets 2.16.1
• Tokenizers 0.15.1