You can deploy this model and start earning money today!

RichardErkhov/
mlfoundations-dev_-_test_run_mini-exl2

Name: mlfoundations-dev_-_test_run_mini-exl2
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

test_run_mini - EXL2

Model creator: https://huggingface.co/mlfoundations-dev/
Original model: https://huggingface.co/mlfoundations-dev/test_run_mini/

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
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/mlfoundations-dev_-_test_run_mini-exl2 test_run_mini-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 mlfoundations-dev_-_test_run_mini-exl2 --revision 6_5 --local-dir test_run_mini-6_5 --local-dir-use-symlinks False

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

huggingface-cli download mlfoundations-dev_-_test_run_mini-exl2 --revision 6_5 --local-dir test_run_mini-6.5 --local-dir-use-symlinks False

Original model description:

library_name: transformers license: llama3.2 base_model: meta-llama/Llama-3.2-1B tags:

llama-factory
full
generated_from_trainer model-index:
name: test_run_mini results: []

test_run_mini

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the llamafactory/alpaca_en dataset. It achieves the following results on the evaluation set:

Loss: 1.4380

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: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 512
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 3

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.1538	3	1.4380

Framework versions

Transformers 4.45.2
Pytorch 2.4.1+cu121
Datasets 2.21.0
Tokenizers 0.20.1

RichardErkhov/mlfoundations-dev_-_test_run_mini-exl2

Available sizes

Download instructions

Original model description:

test_run_mini

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
mlfoundations-dev_-_test_run_mini-exl2