Downloads · 30 days
23
30% of all-time downloads
mengdili_-_sft_openassistant-guanaco-awq
RichardErkhov/mengdili_-_sft_openassistant-guanaco-awq
mengdili_-_sft_openassistant-guanaco-awq is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
76
Public
Parameters
331M
215 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors215 MB · 98%
Parameter types
How the weights are stored.
I32302M · 91%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
sft_openassistant-guanaco - AWQ
- Model creator: https://huggingface.co/mengdili/
- Original model: https://huggingface.co/mengdili/sft_openassistant-guanaco/
Original model description:
license: other base_model: facebook/opt-350m tags:
- trl
- sft
- generated_from_trainer datasets:
- generator model-index:
- name: sft_openassistant-guanaco results: []
<!-- 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. -->
sft_openassistant-guanaco
This model is a fine-tuned version of facebook/opt-350m on the generator dataset.
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: 1.41e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 2048
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Type
- opt
- Created
- Dec 7, 2024
- Updated
- Dec 7, 2024