Downloads · 30 days
19
45% of all-time downloads
andrewbai_-_tinyllama-sft-vicuna-sub-large-user-length-awq
RichardErkhov/andrewbai_-_tinyllama-sft-vicuna-sub-large-user-length-awq
andrewbai_-_tinyllama-sft-vicuna-sub-large-user-length-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
42
Public
Parameters
1.1B
766 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors766 MB · 99%
Parameter types
How the weights are stored.
I32969M · 88%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
tinyllama-sft-vicuna-sub-large-user-length - AWQ
- Model creator: https://huggingface.co/andrewbai/
- Original model: https://huggingface.co/andrewbai/tinyllama-sft-vicuna-sub-large-user-length/
Original model description:
license: apache-2.0 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer datasets:
- ucla-cmllab/vicuna_sub_large_user_length_30k model-index:
- name: tinyllama-sft-vicuna-sub-large-user-length 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. -->
tinyllama-sft-vicuna-sub-large-user-length
This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the ucla-cmllab/vicuna_sub_large_user_length_30k dataset. It achieves the following results on the evaluation set:
- Loss: 0.8082
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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7371 | 0.9979 | 234 | 0.8082 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Type
- llama
- Created
- Dec 15, 2024
- Updated
- Dec 15, 2024